diff --git a/.gitattributes b/.gitattributes
index 7ad24fa8b37274155c373edade1d2e0684016564..1e7bfb42b750dacd8d586bec26d1f53f2ca9d79e 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -1147,3 +1147,118 @@ neuronxcc-2.15.128.0+56dc5a86/MODULE_fbd5df1f3fbd8961b2cf/model.neuron filter=lf
 neuronxcc-2.15.128.0+56dc5a86/MODULE_fc9ec19cff495325a3e0/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.15.128.0+56dc5a86/MODULE_fd4e98821991f79371a5/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.15.128.0+56dc5a86/MODULE_fe924f54747c457b124f/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_1a8a1dcc5602ff8ddec6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_1ca67327d6a02ad353a8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_1cd0565a02c10f144704+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_1effbda15d9f42206720+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_214dc0ee42e04693dbb5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_22e95c6f73dab6388757+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_2c40bd8a6014a02165ab+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_31af802d5e12d5aa028b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_3af717c28066870c7216+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_3b383e30294891125e5a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_40d51447ca85a7759d7f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_40e160d4eaab44c899f3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_4ce00b10fe4f29f6dbe1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_4d56eb1c04b40b3e75de+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_65cdd3c9e39eadcee9b5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_76ab80e50266df202b78+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_7bdbb30804540e0361a7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_833e80aecf8c9fa09aca+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_836447b8784a4f817bed+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_85ebea4bab5db49de85f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_8d41ce0c47e72de277f0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_9473e53f348276a107d1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_a6f4ac2633b6b1d204d5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_b7aecc50b404bc1d53d9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_c5985f85d97aa97e0809+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_c765d50b5542ffc09176+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_c7a4a1ee44b16d426dc5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_db2224cc81def0c8b21c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_dcd22245b4a305171833+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_e28ae2c4e84b1d46a704+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_e8582306f63de0ecc01c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_f661f6721bb3f19918f8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.14.227.0+2d4f85be/MODULE_fa30f35965a9f4fea034+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_00c2465d32b694cdc75a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_0157f35eb303445e190f+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_02bf38a18ccb8af02b13+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_0b70f795f32d979dd08f+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_0bf56f9a64db27448684+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_0de6c682e356929254c6+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_0eeac286e4dde346cdf4+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_107dec43871d718efda8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_127dc040363bce8eb922+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_141ebe85aa9f9d0f05ec+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_15684f4b794e72102d51+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_1948c053c0208cb14f17+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_1f352aa63d57587fec70+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_2004627e11b2e5bd46ba+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_216347c7e726ef8144fe+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_21e3dcaee19883fe287e+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_33719efab65aba8971de+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_365ac1cdaf18d8317ae6+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_37b1814c685ac0d82c92+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_3c471449bded502e03a7+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_3f6d05883b6613774923+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_430e78bb7f185201891d+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_458717ec5cd8e550df87+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_45bedf40dd477066a7fa+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_479422f85ce1f5ebd67a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_5549dfc1cee1cd892362+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_580e488b1c902056533c+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_5ddb9c233d7c07c4b83e+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_5e4c7cfbd9352445f83d+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_5e6dcb3ba87ae7e60d83+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_5ee3ab5ecb033c6bdeae+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_5eefafb0f1f9fc1e59e0+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_6d6c15e58725fa158325+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_703336702854a488dfa4+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_7661d6eadbe802c530f4+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_7719ec8fd597806cec35+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_77f52b3bc8e641473aab+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_79389d88c33464914847+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_7a5881d8f3cfc70fe0d7+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_7c94578e80247ad042b9+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_80adfd88e3f30235a817+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_83867e44a27b65a12481+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_866bbf0d17b9db9b493d+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_87bca61b0e0d50c81990+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_8bdb334c1899e9bed2c5+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_967b0f433d458fa4e23d+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_99a69aadae08714e73ed+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_9ac5df1af559151d7b88+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_9b0eecb5e0b590f9420a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_a0a5efc77c5084df68b7+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_a3426cf68b987d331b3c+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_a4f3f00fbd1b3e7a58a6+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_aaeee402a55cb205f6f8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_b01949283e27a04f0e6e+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_b6f31af295bc1fdd0707+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_b720c31dac82c34258cd+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_b73835229038eafd2762+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_bdf4f86a85b75038b651+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_be4df199a79b7377e53a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_c3e577073bafae1e671b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_c4a2455c5b25dada65d7+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_c548cc651b8f6e85d9e8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_c57f19ed333f0e818ff9+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_c65426c729b86309e34a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_c77c617e0f686c6e9c00+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_cc1727b893df6b3b25c5+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_ce4004e47d7f9259e48d+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_cee1eefa9c3af642bf9b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_d19b002f79730c2890a1+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_d656e4c29e525a64d500+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_d83898ae6200d4ae727b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_dfb4e18dbbfd0e05a6e6+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_e9508c7d41b1f29d36fc+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_ec7ce1cb59fb29fdc73b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_efddfbc496e02d36ff87+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_f10dd3b89a824c879736+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_f34e4ed3c28e63eda19b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_f4d26174266564b9c206+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_f93de83e0c3ea0bb06cc+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_ff1977202245df118119+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24/inference/llama/meta-llama/CodeLlama-7b-Instruct-hf/e4d3f9d8d335e8c2ff1f.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24/inference/llama/meta-llama/CodeLlama-7b-Instruct-hf/e4d3f9d8d335e8c2ff1f.json
new file mode 100644
index 0000000000000000000000000000000000000000..346c8ae35dd7f7e1bfcb714796bcb8403ccc8c87
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24/inference/llama/meta-llama/CodeLlama-7b-Instruct-hf/e4d3f9d8d335e8c2ff1f.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 16384, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/CodeLlama-7b-Instruct-hf", "checkpoint_revision": "4ce0c40b2ea823bd1d8f1f3fd5bc8a7e80d749bc", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 1000000, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32016}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/02b3df5661ef8ff79cc0.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/02b3df5661ef8ff79cc0.json
new file mode 100644
index 0000000000000000000000000000000000000000..699ff25361ac2690e3ee2862a1c342b40e87e999
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/02b3df5661ef8ff79cc0.json
@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "f16", "batch_size": 64, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/4151c6889dcf1584205c.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/4151c6889dcf1584205c.json
new file mode 100644
index 0000000000000000000000000000000000000000..9d035227ec941634fa98534106b0d8e28fe19290
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/4151c6889dcf1584205c.json
@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "f16", "batch_size": 32, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/6d5c143cd18bfcd9f4af.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/6d5c143cd18bfcd9f4af.json
new file mode 100644
index 0000000000000000000000000000000000000000..e96cd154288c8bf2da917aab214557f64f3d40f1
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/6d5c143cd18bfcd9f4af.json
@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 128, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/874f10ed32bff7260c79.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/874f10ed32bff7260c79.json
new file mode 100644
index 0000000000000000000000000000000000000000..1166b99a59618c0bd04870baf0f966a7ed71ede0
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/874f10ed32bff7260c79.json
@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "f16", "batch_size": 64, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 128, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/befa24d60d5bca012c3b.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/befa24d60d5bca012c3b.json
new file mode 100644
index 0000000000000000000000000000000000000000..7bf2b03511bc17d655a8d1b55f2da510e81a9346
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/gpt2/befa24d60d5bca012c3b.json
@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "f16", "batch_size": 1, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/bba017603eba49cc3a1f.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/bba017603eba49cc3a1f.json
new file mode 100644
index 0000000000000000000000000000000000000000..8405659dee6898537b1b126d06490db51639477e
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/bba017603eba49cc3a1f.json
@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 512, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/openai-community/gpt2/180283e8bf01ae3507c0.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/openai-community/gpt2/180283e8bf01ae3507c0.json
new file mode 100644
index 0000000000000000000000000000000000000000..97a9ec3921f30171c0977cb80e95e6097f2aae6e
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/openai-community/gpt2/180283e8bf01ae3507c0.json
@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "openai-community/gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/openai-community/gpt2/39a7649c623c1888c776.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/openai-community/gpt2/39a7649c623c1888c776.json
new file mode 100644
index 0000000000000000000000000000000000000000..01822773e614bb4f7a50e05e9991b3ad1b64f6ba
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/openai-community/gpt2/39a7649c623c1888c776.json
@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "openai-community/gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/openai-community/gpt2/54e96fc83b91f9ca40c8.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/openai-community/gpt2/54e96fc83b91f9ca40c8.json
new file mode 100644
index 0000000000000000000000000000000000000000..3df05775d14954a25ceb7fb8dfddc2d2a0078ea0
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/gpt2/openai-community/gpt2/54e96fc83b91f9ca40c8.json
@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "openai-community/gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/54d2c115427eb106b498.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/54d2c115427eb106b498.json
new file mode 100644
index 0000000000000000000000000000000000000000..c111446624d682b0e9bba77778d844a76106b690
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/54d2c115427eb106b498.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-Instruct", "checkpoint_revision": "e1945c40cd546c78e41f1151f4db032b271faeaa", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 8192, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/55063f94fc7dddda3ac1.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/55063f94fc7dddda3ac1.json
new file mode 100644
index 0000000000000000000000000000000000000000..91e8ff99eca0c592d81cc285d19692ab8323e584
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/55063f94fc7dddda3ac1.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-Instruct", "checkpoint_revision": "e1945c40cd546c78e41f1151f4db032b271faeaa", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 2048, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/832467c16a81d475fbb1.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/832467c16a81d475fbb1.json
new file mode 100644
index 0000000000000000000000000000000000000000..1e3140c432d4fd6422fe148a44bdc000cbb125cd
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/832467c16a81d475fbb1.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-Instruct", "checkpoint_revision": "e1945c40cd546c78e41f1151f4db032b271faeaa", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/9a95ca98317aed241916.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/9a95ca98317aed241916.json
new file mode 100644
index 0000000000000000000000000000000000000000..e486fd9817d5a9363fd56ccea6bae36cb52ee6fb
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/9a95ca98317aed241916.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-Instruct", "checkpoint_revision": "e1945c40cd546c78e41f1151f4db032b271faeaa", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 8192, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/a246f0054be6283dfb7e.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/a246f0054be6283dfb7e.json
new file mode 100644
index 0000000000000000000000000000000000000000..3eab8e608799afe56160551a8441f32595401bed
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/a246f0054be6283dfb7e.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-Instruct", "checkpoint_revision": "e1945c40cd546c78e41f1151f4db032b271faeaa", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 2048, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/b92e78445e785f8ec26d.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/b92e78445e785f8ec26d.json
new file mode 100644
index 0000000000000000000000000000000000000000..c8e9eb60f9ff76e0f15cc39140c78b1df73e016d
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/b92e78445e785f8ec26d.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 16, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-Instruct", "checkpoint_revision": "e1945c40cd546c78e41f1151f4db032b271faeaa", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/f1b87f52657555ab6e8e.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/f1b87f52657555ab6e8e.json
new file mode 100644
index 0000000000000000000000000000000000000000..8663997dd405e462a43ca5f6f237893dd6cadc4e
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B-Instruct/f1b87f52657555ab6e8e.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "meta-llama/Meta-Llama-3-8B-Instruct", "checkpoint_revision": "e1945c40cd546c78e41f1151f4db032b271faeaa", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/2a30c91813b1e7196f95.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/2a30c91813b1e7196f95.json
new file mode 100644
index 0000000000000000000000000000000000000000..5d4b3e8accd669a153275edce79e6dd904ae0362
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/2a30c91813b1e7196f95.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 8, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/6434dcc45c7c9439f30f.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/6434dcc45c7c9439f30f.json
new file mode 100644
index 0000000000000000000000000000000000000000..a5256a4dcad8b67810f3b1b549afaedd95e79481
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/6434dcc45c7c9439f30f.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 16, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/7e91caedb706bd96bd3a.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/7e91caedb706bd96bd3a.json
new file mode 100644
index 0000000000000000000000000000000000000000..d517f834d29aa5cedcc40d2cfe4431479f684838
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/7e91caedb706bd96bd3a.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/f22f49b5301c6c906c34.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/f22f49b5301c6c906c34.json
new file mode 100644
index 0000000000000000000000000000000000000000..b0a97de775a56bd2a6f7786181f55497d98d57bd
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/f22f49b5301c6c906c34.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/fd9b28c3749a3bbd30c5.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/fd9b28c3749a3bbd30c5.json
new file mode 100644
index 0000000000000000000000000000000000000000..94a68132d577cbe08fbbfee13358b6a626b2c9e3
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/fd9b28c3749a3bbd30c5.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 32, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B-Instruct/1b591b403ed491d5ab63.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B-Instruct/1b591b403ed491d5ab63.json
new file mode 100644
index 0000000000000000000000000000000000000000..e1ac61452803d8abcce141453a9439332c799b51
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B-Instruct/1b591b403ed491d5ab63.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B-Instruct", "checkpoint_revision": "5206a32e0bd3067aef1ce90f5528ade7d866253f", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/vit/hf-internal-testing/tiny-random-vit/d41951caf693837ced38.json b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/vit/hf-internal-testing/tiny-random-vit/d41951caf693837ced38.json
new file mode 100644
index 0000000000000000000000000000000000000000..216700c511325a38a8d74746fdfde0c04f86d5df
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/vit/hf-internal-testing/tiny-random-vit/d41951caf693837ced38.json
@@ -0,0 +1 @@
+{"architectures": ["ViTForImageClassification"], "attention_probs_dropout_prob": 0.1, "encoder_stride": 16, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "image_size": 30, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-12, "model_type": "vit", "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "disable_fallback": false, "disable_fast_relayout": false, "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_image_size": 30, "static_num_channels": 3, "static_patch_size": 2}, "num_attention_heads": 4, "num_channels": 3, "num_hidden_layers": 5, "patch_size": 2, "qkv_bias": true, "task": "image-classification", "vocab_size": {}}
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..225576bdd321bcdfe2c00a9b58fcad483bf38dea
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b8e8daf6532c7ead9f96cb22a851fa5f5465806aa4650fed38b0670e63a2872
+size 405658
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..2de5a4ca4be3af50c23e9909e8511b8ca9e0a575
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_0c9ea6bf6c6bea6f03e0+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f987b57583f4739daa220d72544bc18b9c78e20ac7e62b76232d9daad774284
+size 19508224
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..af4b5ee9dd4ad8fa02833a4958b0e418603ef775
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed1245ea53f899f203393f819f171f96c1e84311a192afe32ce923432b378aa
+size 263859
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..56a6387b802faf29df7a1397b60ec07a0b951427
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_0d1965059c9351f7704e+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8749dd44b2b1c4f9ac28dd73f12f7cdd62d274e45f7031ac573be143f5b159b7
+size 1711104
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1140b8ce94a49c64dc0a+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1140b8ce94a49c64dc0a+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1140b8ce94a49c64dc0a+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1140b8ce94a49c64dc0a+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1140b8ce94a49c64dc0a+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..116868d98937d189647e6c5a386a9ee0ce4dda70
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1140b8ce94a49c64dc0a+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76060ba0acde6101e4b19635759494e2738bcb9f409dac02f9450d1f97c9111b
+size 9926
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1140b8ce94a49c64dc0a+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1140b8ce94a49c64dc0a+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..f3cc26a5f4c1ed1fd4b8f52ada55a74265a6f855
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1140b8ce94a49c64dc0a+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_13824a02aaaf61dc8bcb+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_13824a02aaaf61dc8bcb+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_13824a02aaaf61dc8bcb+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_13824a02aaaf61dc8bcb+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_13824a02aaaf61dc8bcb+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..daa0a98093cf9a506117f3e96b06f102f38ed32d
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_13824a02aaaf61dc8bcb+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d78f781f32eda7c36b1b6b06560f10237ac5941b291768a6dd1771c96808dae
+size 49626
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_13824a02aaaf61dc8bcb+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_13824a02aaaf61dc8bcb+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..aa6b5c95dfb27470ecfbe14f76e2db42d172c19b
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_13824a02aaaf61dc8bcb+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1410a6ac4741f5c2dc66+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1410a6ac4741f5c2dc66+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1410a6ac4741f5c2dc66+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1410a6ac4741f5c2dc66+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1410a6ac4741f5c2dc66+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..b69ac20748491af97baec4a17b775420b6c072a4
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1410a6ac4741f5c2dc66+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:020d99880f04a1d73c17c2d2e12f8b30c4a34ab852f68872d9938cf298911db4
+size 137155
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1410a6ac4741f5c2dc66+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1410a6ac4741f5c2dc66+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..058e01fbc1f2cecf746d6b38e44ea43905217201
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1410a6ac4741f5c2dc66+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1817a7b2bbf2fa9752a7+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1817a7b2bbf2fa9752a7+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1817a7b2bbf2fa9752a7+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1817a7b2bbf2fa9752a7+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1817a7b2bbf2fa9752a7+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..a7fb3a0266c3edd3f74f50f67caf19593f504181
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1817a7b2bbf2fa9752a7+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de465b2d26253b2c172b13a940eb18679e418d7ed6a522cd399a9d22ea98276
+size 137155
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1817a7b2bbf2fa9752a7+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1817a7b2bbf2fa9752a7+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..86b1238284df38917185f4c2caabd4b18e17f446
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1817a7b2bbf2fa9752a7+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_182575e7fb323521e978+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_182575e7fb323521e978+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_182575e7fb323521e978+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_182575e7fb323521e978+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_182575e7fb323521e978+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..f1fb1f1ae04234ff0bf636285010f2fca56a0d69
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_182575e7fb323521e978+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce76c639689087fafee7b701946ea73d7cb9552986aac9d8c3f6ee690bb5e79
+size 137347
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_182575e7fb323521e978+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_182575e7fb323521e978+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..70eb07875c5eaa3482167db94857871d65896f1e
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_182575e7fb323521e978+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1a8a1dcc5602ff8ddec6+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1a8a1dcc5602ff8ddec6+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1a8a1dcc5602ff8ddec6+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1a8a1dcc5602ff8ddec6+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1a8a1dcc5602ff8ddec6+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..a19cddd5682c307010da472239f303eea24d9009
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1a8a1dcc5602ff8ddec6+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cfdcee8f091f106f06c7a56b329f582076bc1da4c152683076aa230e87fe56c
+size 446653
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1a8a1dcc5602ff8ddec6+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1a8a1dcc5602ff8ddec6+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b8bc8a84d22b1aeb6d467b45e51814e7c00be7d0
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1a8a1dcc5602ff8ddec6+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa1a6bf375c283388ca78fb71d76f821df577d83c5ea1713b869b181b9eecd7
+size 42302464
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1b2f42bbcb326d58aca8+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1b2f42bbcb326d58aca8+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1b2f42bbcb326d58aca8+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1b2f42bbcb326d58aca8+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1b2f42bbcb326d58aca8+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..bf4d24ca1bee54216c879fddf4688bd33fde2757
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1b2f42bbcb326d58aca8+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18737b5c5d14209cbdb5cec1f1d54479fe50fd5742e276c2d1f84fb7bb35338
+size 137347
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1b2f42bbcb326d58aca8+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1b2f42bbcb326d58aca8+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..94a0a8952d289f4304a3cf2d1210612be73e7ca5
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1b2f42bbcb326d58aca8+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1bb270c9a7c0af6647b1+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1bb270c9a7c0af6647b1+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1bb270c9a7c0af6647b1+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1bb270c9a7c0af6647b1+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1bb270c9a7c0af6647b1+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..998f5024c19ce7a49bbc19e2d683aea0bee8df52
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1bb270c9a7c0af6647b1+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:677e8b007a90747686051a0014e107a71fffe28dde418ddd6ff930208c657a45
+size 137347
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1bb270c9a7c0af6647b1+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1bb270c9a7c0af6647b1+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..2e18dbfb38b849d674856945b1a77678ef9cd573
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1bb270c9a7c0af6647b1+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1c7cb91bfbb79b66f457+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1c7cb91bfbb79b66f457+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1c7cb91bfbb79b66f457+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1c7cb91bfbb79b66f457+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1c7cb91bfbb79b66f457+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..58be7b94a465265230aa08f707215222b4780711
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1c7cb91bfbb79b66f457+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d34bd3963e84a71ee3c82bcab1c9c061d56b1b6ffcdd251fb762e3fc09ebfa4
+size 137347
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1c7cb91bfbb79b66f457+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1c7cb91bfbb79b66f457+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..4234cf2878a6b12c572e265ee8c9ee0ff42a22fc
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1c7cb91bfbb79b66f457+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1ca67327d6a02ad353a8+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1ca67327d6a02ad353a8+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1ca67327d6a02ad353a8+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1ca67327d6a02ad353a8+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1ca67327d6a02ad353a8+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..d1842a869ea2ae2c53749e6d1ee5af4dd3ee9054
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1ca67327d6a02ad353a8+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e50ea8ccebb0073affe977c07aa1a48d43618be45990eac513d5a1d955e6544
+size 266266
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1ca67327d6a02ad353a8+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1ca67327d6a02ad353a8+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..72d7c6baf6c9209479ccad3bd805ca58597b71ab
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1ca67327d6a02ad353a8+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ca5987289a89d684d46488ed424334f41fb6e9a24bcb0eb1e22ff767a60235
+size 6872064
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1cd0565a02c10f144704+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1cd0565a02c10f144704+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1cd0565a02c10f144704+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1cd0565a02c10f144704+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1cd0565a02c10f144704+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..2e937df4fecee6de997e633fbd802aa6a500a367
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1cd0565a02c10f144704+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c84b7711281ef6ff6875ca05a0914cfb924ac141e496f5c96b6aa6a222a6d2f
+size 446653
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1cd0565a02c10f144704+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1cd0565a02c10f144704+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..be1b5a6901d4cea9ada0ec6edad5a8f69e562143
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1cd0565a02c10f144704+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386e3a64375202cd51b885fd453891721402b55cd29d811c60f8afcb402dd5c0
+size 19078144
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1effbda15d9f42206720+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1effbda15d9f42206720+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1effbda15d9f42206720+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1effbda15d9f42206720+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1effbda15d9f42206720+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..eee7772ea9000f7caa8799f37a43d4918bb92787
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1effbda15d9f42206720+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:378c70ae3d593c390040666cb307a30ce9fe03dd78b77bce6a27212eaded53d4
+size 333872
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_1effbda15d9f42206720+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1effbda15d9f42206720+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..faccee3de0582429092517947bedf185a5a56f87
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_1effbda15d9f42206720+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e0bd69a20695c03518fdc43a7a98d152cdde5a7effffa23eab771009354679
+size 2438144
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_214dc0ee42e04693dbb5+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_214dc0ee42e04693dbb5+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_214dc0ee42e04693dbb5+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_214dc0ee42e04693dbb5+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_214dc0ee42e04693dbb5+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..7f4672075b48cb543c9aac0df4ece3ee1c465a42
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_214dc0ee42e04693dbb5+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9dd1155242f7c5104ebad645e63170144a354e718b57e76d8ba991762fc75ec
+size 266266
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_214dc0ee42e04693dbb5+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_214dc0ee42e04693dbb5+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..5b054fca035ca56a03a7c05abd0a952437d32eca
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_214dc0ee42e04693dbb5+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06186a2828f3563f78375b1a11feb74ae31774d6e4429e50735e7925afa9c4e6
+size 3902464
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_22e95c6f73dab6388757+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_22e95c6f73dab6388757+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_22e95c6f73dab6388757+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_22e95c6f73dab6388757+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_22e95c6f73dab6388757+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..4915964023105f42abd24965b25e6e01528d3131
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_22e95c6f73dab6388757+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e132a0ef7c60598fcb5edd38dca695eb2ac20822a7a6700f5460ab561e0b8d26
+size 333872
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_22e95c6f73dab6388757+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_22e95c6f73dab6388757+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..3235f0dd51bc1cedc7fd08ecf937c8cc379fd8da
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_22e95c6f73dab6388757+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca06d25d998769fd0c3fb78d7a2c0832e28e6d5bdf18ccc3ba0bc2fa0adfb2e
+size 2632704
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_252402fc5619b980dd9b+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_252402fc5619b980dd9b+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_252402fc5619b980dd9b+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_252402fc5619b980dd9b+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_252402fc5619b980dd9b+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..a342ff05620361fea775f3b95cc829a925ff3f48
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_252402fc5619b980dd9b+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca8631202b27daccf00225235a1be40c634fd1b5d726993fa935b4d8d78045f
+size 23834
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_252402fc5619b980dd9b+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_252402fc5619b980dd9b+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..0f2fea99beb2ca20371b5a85278bd59ebb3fd318
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_252402fc5619b980dd9b+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_2c40bd8a6014a02165ab+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_2c40bd8a6014a02165ab+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_2c40bd8a6014a02165ab+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_2c40bd8a6014a02165ab+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_2c40bd8a6014a02165ab+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..80a52614a72d8aff25b9685d6a6f1921bef7293e
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_2c40bd8a6014a02165ab+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f04357ee8123726337494194eab5a0162cf1b805b6d607c15b17ac7b0fbef65d
+size 333872
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_2c40bd8a6014a02165ab+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_2c40bd8a6014a02165ab+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..ac5e8f990302e14b223c0620f77fedbc6decd179
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_2c40bd8a6014a02165ab+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94366a46e6c4ad6b4ca9601c634774554d688bfec91ab92097905f83054197b6
+size 2509824
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_2dd0fa8e16b6777d4f80+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_2dd0fa8e16b6777d4f80+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_2dd0fa8e16b6777d4f80+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_2dd0fa8e16b6777d4f80+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_2dd0fa8e16b6777d4f80+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..ab4fd55dda72ec52749ad095cfd481edcf1bdc0c
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_2dd0fa8e16b6777d4f80+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab30ed0f826bd5b5e7459999e7b847f03bdd0f7873d53aef26444d9faf5d084
+size 137155
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_2dd0fa8e16b6777d4f80+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_2dd0fa8e16b6777d4f80+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..ded7ba46ee37fe2bbd5db20c682f53aba18667ac
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_2dd0fa8e16b6777d4f80+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_31af802d5e12d5aa028b+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_31af802d5e12d5aa028b+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_31af802d5e12d5aa028b+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_31af802d5e12d5aa028b+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_31af802d5e12d5aa028b+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..03c48bf871fbdd0965350e6debe4c556f101486c
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_31af802d5e12d5aa028b+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd492b4c9e5bcf570584ea398cce776458d722a64ae2f72de3f4567e0fcc24e8
+size 267290
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_31af802d5e12d5aa028b+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_31af802d5e12d5aa028b+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..7ffdb63825c541c54bd8a1500277174b37b15ae7
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_31af802d5e12d5aa028b+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c25dee375b83649832dbe4c41e03bf6b716c245a757380a0c6fb7e8425c3182b
+size 2448384
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_38a2244561bb242d717d+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_38a2244561bb242d717d+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_38a2244561bb242d717d+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_38a2244561bb242d717d+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_38a2244561bb242d717d+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..86a87dd4721ce600270b22a16ee1470a752504e6
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_38a2244561bb242d717d+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712b8b3fa5f45a2b017353bb5b51e7117d3549c75e5ae8bb908debf5f4d7c582
+size 56579
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_38a2244561bb242d717d+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_38a2244561bb242d717d+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..e9935e07a26e481b59c672e4a4b01ac5aa5b1a58
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_38a2244561bb242d717d+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_3af717c28066870c7216+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_3af717c28066870c7216+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_3af717c28066870c7216+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_3af717c28066870c7216+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_3af717c28066870c7216+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..6264e8ac16490b2abe95f75f1a95a513b0fad84d
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_3af717c28066870c7216+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d175a455a0b1edebe23b93faf89b33609dc3b2b76678c3f6cbaf2710425a7ccf
+size 267290
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_3af717c28066870c7216+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_3af717c28066870c7216+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..46e6200776dc2aa57f698ba6521fdbbc94c5a6e8
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_3af717c28066870c7216+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3a22fed789c5bef60e6527c07b0fcdac6deb2e3772241f907303bcb324b458
+size 4404224
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_3b383e30294891125e5a+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_3b383e30294891125e5a+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_3b383e30294891125e5a+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_3b383e30294891125e5a+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_3b383e30294891125e5a+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..55fcedd9cee733cbd158e071df990e14997ff825
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_3b383e30294891125e5a+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87715c23fb350db06c39bf442a641789345de8c9ca00405b2af275fe3609cf13
+size 334896
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_3b383e30294891125e5a+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_3b383e30294891125e5a+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..3993f7a787a3716a7577d64c5435993eb6f9e8bc
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_3b383e30294891125e5a+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb9f364feeb3219a59f64d5d8676cfe498de6ae99fd2dbfb1db2dc50fbb12835
+size 1414144
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_40d51447ca85a7759d7f+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_40d51447ca85a7759d7f+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_40d51447ca85a7759d7f+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_40d51447ca85a7759d7f+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_40d51447ca85a7759d7f+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..319b55fb3f347f93bb60e0174457d2d646863b98
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_40d51447ca85a7759d7f+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c125f9bab1ce9ad2db5b32a068037bf7998016b4eedf459002403cec43a3cbf2
+size 361605
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_40d51447ca85a7759d7f+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_40d51447ca85a7759d7f+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..6e4ea5368c51262e089af35d56f57918484f3838
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_40d51447ca85a7759d7f+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2831a5a887dfa13f3ab6156c56d2725b9ff918816f8fb3312ebbd1173b312f5d
+size 3257344
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_40e160d4eaab44c899f3+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_40e160d4eaab44c899f3+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_40e160d4eaab44c899f3+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_40e160d4eaab44c899f3+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_40e160d4eaab44c899f3+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..116b267b0ad30da9fc33e6c81529985edd7ccbd1
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_40e160d4eaab44c899f3+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ee4c8eb0c9c36453e12b90928135e3543ffc1e2e422a6d2eb39e63f7968384
+size 333872
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_40e160d4eaab44c899f3+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_40e160d4eaab44c899f3+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..9226d869ce2a55f105681bc7238c19a2c91925b4
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_40e160d4eaab44c899f3+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:657db3a47e9b174be1b1aeb0136e7123ac5b28bed9e9405a84fd14bac5ea94ef
+size 2386944
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_47b8dd8252dc681e14c3+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_47b8dd8252dc681e14c3+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_47b8dd8252dc681e14c3+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_47b8dd8252dc681e14c3+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_47b8dd8252dc681e14c3+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..b41fa676a5b85053966d1f786980409469e20da5
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_47b8dd8252dc681e14c3+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2978040780035c8ace7b68a3bc8012c442cc068c2337199b9a88d269385a4878
+size 24183
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_47b8dd8252dc681e14c3+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_47b8dd8252dc681e14c3+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..bf2ac0d61712a33eb94b129cda1da0be08695c9e
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_47b8dd8252dc681e14c3+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_4ce00b10fe4f29f6dbe1+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_4ce00b10fe4f29f6dbe1+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_4ce00b10fe4f29f6dbe1+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_4ce00b10fe4f29f6dbe1+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_4ce00b10fe4f29f6dbe1+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..08c5345d895e6d79617d0943b7cbf395cb57a6f1
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_4ce00b10fe4f29f6dbe1+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:341cd706e464017c732360e98845703348b35b145be91df4dd2ae0ec8a3f0d4f
+size 267290
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_4ce00b10fe4f29f6dbe1+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_4ce00b10fe4f29f6dbe1+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..9d7d0005de4d6d225d929595d3630811791f7bea
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_4ce00b10fe4f29f6dbe1+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e528f25c895426f26ceba2a5da9f38cf9622132f85f21c811a4441afd358a1
+size 8643584
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_4d56eb1c04b40b3e75de+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_4d56eb1c04b40b3e75de+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_4d56eb1c04b40b3e75de+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_4d56eb1c04b40b3e75de+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_4d56eb1c04b40b3e75de+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..c03859c62d39ff9995ffbe73a46a79998af4e287
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_4d56eb1c04b40b3e75de+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:754b79574402d533b907d97e5a0d09cb6d3add2573196001083b16860e171060
+size 334896
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_4d56eb1c04b40b3e75de+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_4d56eb1c04b40b3e75de+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..ce97712c4944b5862db9026820944a9f180938b2
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_4d56eb1c04b40b3e75de+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15b2a312e5fba0e0d58969bbc02b1d8a235d4e36b7bde2cf30a1bad6646da13c
+size 1393664
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_51cf81c173fe76caf43f+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_51cf81c173fe76caf43f+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_51cf81c173fe76caf43f+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_51cf81c173fe76caf43f+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_51cf81c173fe76caf43f+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..21a262f3e7c77288c4f0271a3f67cbfb0773c1aa
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_51cf81c173fe76caf43f+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:318b2e7a06d6d31cd90eea7f8a541f0a6823bf31d6287cdbfc08d97349930143
+size 56579
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_51cf81c173fe76caf43f+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_51cf81c173fe76caf43f+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..01a67da6cd52372e8ebad5a95dc750361c3b7039
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_51cf81c173fe76caf43f+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_5223febc5552b72957f0+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_5223febc5552b72957f0+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_5223febc5552b72957f0+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_5223febc5552b72957f0+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_5223febc5552b72957f0+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..f8abc536f3f715ada4f45efdc0d7fd8f0c85df71
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_5223febc5552b72957f0+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb58748f4a84279f4bd76ff579f0e98ef844779c2a8cd305d72b4c9c7b9ca23c
+size 137347
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_5223febc5552b72957f0+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_5223febc5552b72957f0+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..fc796f1a1d43e63ebe07e59cbdd2a581a386bd91
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_5223febc5552b72957f0+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_5dbdd0740e6833e0396f+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_5dbdd0740e6833e0396f+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_5dbdd0740e6833e0396f+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_5dbdd0740e6833e0396f+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_5dbdd0740e6833e0396f+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..02634b00f533c75c7d829df6ab948a75cdee73e7
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_5dbdd0740e6833e0396f+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c869ea552066960f8f755dfb54aa311d23ff625ede7eda4946a983bc91b9a1
+size 135795
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_5dbdd0740e6833e0396f+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_5dbdd0740e6833e0396f+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..ba5292b9200ccf15ad6ef32c242fe2cd9fccb517
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_5dbdd0740e6833e0396f+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_61e24129bee22f9fb911+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_61e24129bee22f9fb911+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_61e24129bee22f9fb911+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_61e24129bee22f9fb911+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_61e24129bee22f9fb911+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..aae53e49303d65ae693cbba90b625a3ff79999e6
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_61e24129bee22f9fb911+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703f36fa787d54cf10fa7cc9c995b754174d18339ca8897efdbcabe3cb562051
+size 56579
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_61e24129bee22f9fb911+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_61e24129bee22f9fb911+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..29dadbf3643aea1cfaa9f9bcf768547ec49cbf09
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_61e24129bee22f9fb911+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_65cdd3c9e39eadcee9b5+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_65cdd3c9e39eadcee9b5+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_65cdd3c9e39eadcee9b5+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_65cdd3c9e39eadcee9b5+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_65cdd3c9e39eadcee9b5+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..e0b8449d36d89aaa668d8a0ebf7bc4f532ec6b97
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_65cdd3c9e39eadcee9b5+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b4c93ced4a2891700fd973d436d2b2d822e36b92b86ca2df99190232be8073
+size 361605
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_65cdd3c9e39eadcee9b5+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_65cdd3c9e39eadcee9b5+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..0eef2895b05f9dc96f5835ea94d3af29ebe67d65
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_65cdd3c9e39eadcee9b5+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3065865413b5ab82f42e73739a843212fd25deb57a4360b4c421935f69e28f56
+size 2407424
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_7340a6540ebf79b230bf+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7340a6540ebf79b230bf+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7340a6540ebf79b230bf+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_7340a6540ebf79b230bf+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7340a6540ebf79b230bf+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..2743f2cda64c92e86c2e3a333950d27022dba78f
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7340a6540ebf79b230bf+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc5fc36eebe4a2142da3e8645cc2c8468a52b4ec691c1e6b4747188ed6c49ab
+size 136806
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_7340a6540ebf79b230bf+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7340a6540ebf79b230bf+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..7608f68e72654f70a7f69717730cb748adba52fa
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7340a6540ebf79b230bf+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_76ab80e50266df202b78+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_76ab80e50266df202b78+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_76ab80e50266df202b78+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_76ab80e50266df202b78+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_76ab80e50266df202b78+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..2c663fdcd78dfcd36960914fc740b51d45d0d5f9
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_76ab80e50266df202b78+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1b8351f66e4eba4ffe032a50335838e97c3a769586df09ca9b806afcd260345
+size 266266
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_76ab80e50266df202b78+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_76ab80e50266df202b78+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b6629fa60c3bd42ee402cf276dc79b3945a7a5d8
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_76ab80e50266df202b78+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78891c9ef9bd122a44fd06db543a47a9d5cb52e73191b6242a105b0a28c24c1
+size 14500864
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_7bdbb30804540e0361a7+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7bdbb30804540e0361a7+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7bdbb30804540e0361a7+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_7bdbb30804540e0361a7+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7bdbb30804540e0361a7+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..b941912636e92f75adb02a257c305e5601bb9bbb
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7bdbb30804540e0361a7+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34521ecd0dd2303e210c653366e59c888c30709108f652b6bba22dea3445c965
+size 361605
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_7bdbb30804540e0361a7+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7bdbb30804540e0361a7+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..d5109100b880f0af09f1dfd52a29c196f907c31d
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7bdbb30804540e0361a7+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44754416698ba233cfa56217d14a429be7639f6847883d34f452eacb2c627d8e
+size 7988224
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_7e61499f72f2d263d632+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7e61499f72f2d263d632+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7e61499f72f2d263d632+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_7e61499f72f2d263d632+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7e61499f72f2d263d632+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..97a577d962c4b9351b08cc5231407571bc2c0fc1
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7e61499f72f2d263d632+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43a7f892e6a38fabdcb936800723b94f089a316f6c68610051394f3d9866f41
+size 1709
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_7e61499f72f2d263d632+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7e61499f72f2d263d632+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..a41cfc890b6bba1a6a92a0ce36fc3101bb475f9d
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_7e61499f72f2d263d632+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_833e80aecf8c9fa09aca+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_833e80aecf8c9fa09aca+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_833e80aecf8c9fa09aca+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_833e80aecf8c9fa09aca+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_833e80aecf8c9fa09aca+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..08c69b696ad78b4fca88b9f06a0f712145ae24de
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_833e80aecf8c9fa09aca+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e6bb9995cfba7335f8ba194b590bde841da13138f536ea15794ef6641751f4
+size 446653
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_833e80aecf8c9fa09aca+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_833e80aecf8c9fa09aca+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..bfb7e9912f34a6a5641a06d94bdeac73b5470d11
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_833e80aecf8c9fa09aca+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1dd2fcaa127036a989094bd9eeadfdefc765ea1cba8a546c534b1ce19bced7
+size 19078144
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_836447b8784a4f817bed+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_836447b8784a4f817bed+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_836447b8784a4f817bed+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_836447b8784a4f817bed+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_836447b8784a4f817bed+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..b8940af4f0b9d3c128a52c81d90ea83912149fe3
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_836447b8784a4f817bed+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19475accc1aad98aa54b04649d20fe63dfab19b35dfda060712d8a91bf71c57b
+size 266266
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_836447b8784a4f817bed+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_836447b8784a4f817bed+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..3b34c0aa1abd69fc2f9496b678ea373393f8a0f3
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_836447b8784a4f817bed+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48bd6bba0ef9dddac3b44aca52819ede84e8ebac12781e7efb5b63d270935da1
+size 3329024
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_85ebea4bab5db49de85f+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_85ebea4bab5db49de85f+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_85ebea4bab5db49de85f+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_85ebea4bab5db49de85f+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_85ebea4bab5db49de85f+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..3b317319a165eef77f2436d3f8ccd8d8f902ddca
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_85ebea4bab5db49de85f+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b771819dc742286fb8dacba0dd150c418058b17ab25a2d9236be523b67a93c
+size 308287
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_85ebea4bab5db49de85f+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_85ebea4bab5db49de85f+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..05d662ed183d70e6e9d37894da9dc48f50297827
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_85ebea4bab5db49de85f+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525915a64a6328b4ea80bb04658d753cf7f92cc49d5a8403dec07d53c6971bec
+size 8561664
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_8710d24afbf59357118f+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8710d24afbf59357118f+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8710d24afbf59357118f+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_8710d24afbf59357118f+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8710d24afbf59357118f+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..f17f0e5c41ac27e774f647940bd60e1580c1e71e
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8710d24afbf59357118f+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11757b47966d03917ac67e7b1f94e95bfc573d5eda798f9f9f8e92aa74756791
+size 9668
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_8710d24afbf59357118f+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8710d24afbf59357118f+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..d558de18cbe84070be067dbc97bf743830e8b9a2
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8710d24afbf59357118f+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_8d41ce0c47e72de277f0+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8d41ce0c47e72de277f0+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8d41ce0c47e72de277f0+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_8d41ce0c47e72de277f0+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8d41ce0c47e72de277f0+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..ce5c81696195826f53ce31410c671f3a9fbdd420
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8d41ce0c47e72de277f0+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69359edd47b5e7abcf06b8ee85c2eef95437f776dc4432f826cd2076057070a4
+size 262835
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_8d41ce0c47e72de277f0+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8d41ce0c47e72de277f0+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..4f2d5f284fb62bd1e8cb2013ddda135257c6f6fb
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8d41ce0c47e72de277f0+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863a73b59f7a96d2f47e8601637469fa3b5586737444b69d668463a2335b341d
+size 3032064
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_8ee1d262124c0d5ab304+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8ee1d262124c0d5ab304+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8ee1d262124c0d5ab304+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_8ee1d262124c0d5ab304+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8ee1d262124c0d5ab304+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..3781a2872e5af00fe86796b6e28ec16c63b3ad87
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8ee1d262124c0d5ab304+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b3b077ccfafbb9a4039db3cef5fcb4184e4ab380afb4d221698cdea7d39ddb3
+size 46096
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_8ee1d262124c0d5ab304+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8ee1d262124c0d5ab304+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..1b63366633c6a59b3f32c1af49e6d6dfccd5c7d4
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_8ee1d262124c0d5ab304+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_9473e53f348276a107d1+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_9473e53f348276a107d1+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_9473e53f348276a107d1+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_9473e53f348276a107d1+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_9473e53f348276a107d1+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..f17c78a84e664ddff10b4a627596ac415a7e0135
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_9473e53f348276a107d1+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f40bea4ebc7fea202041a6167b638e432b170e7aa0746fcd6f8eecf0baf5fb55
+size 333872
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_9473e53f348276a107d1+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_9473e53f348276a107d1+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..e3b4ff4cb97eee62ed30dd0814e229f4b762b588
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_9473e53f348276a107d1+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a06d8ec324cfeab7e31319d5afbc72dd20bb8875d4b83992c6fcf3355e709f
+size 2386944
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_96ec1d0c186f9e541a29+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_96ec1d0c186f9e541a29+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_96ec1d0c186f9e541a29+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_96ec1d0c186f9e541a29+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_96ec1d0c186f9e541a29+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..c7176186af4cb807a371e429308b47d7329df76d
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_96ec1d0c186f9e541a29+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dcb273c8ceaf1c026aa3ecde984cb54d94b3359fd3f16927e64dc05f957624a
+size 49371
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_96ec1d0c186f9e541a29+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_96ec1d0c186f9e541a29+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..83d4f86b2de804b0d96f9e0b0ce14d40ae071a87
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_96ec1d0c186f9e541a29+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_97392b7af08cbab1d8ff+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_97392b7af08cbab1d8ff+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_97392b7af08cbab1d8ff+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_97392b7af08cbab1d8ff+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_97392b7af08cbab1d8ff+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..f9461875873052c503ec82508e4bab84cf04a003
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_97392b7af08cbab1d8ff+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b0a360e1f763e561b128d6074e8e0ebc471f8a177971d4e0791669e7707583c
+size 1709
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_97392b7af08cbab1d8ff+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_97392b7af08cbab1d8ff+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..361cf6935341dd9b3736aa00593b79192bf26da1
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_97392b7af08cbab1d8ff+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_a6f4ac2633b6b1d204d5+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_a6f4ac2633b6b1d204d5+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_a6f4ac2633b6b1d204d5+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_a6f4ac2633b6b1d204d5+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_a6f4ac2633b6b1d204d5+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..f5b7bb380c9c3c84927b85d9e7133d107f6c304b
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_a6f4ac2633b6b1d204d5+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5136bfe226a81b00a57243cf968299373900fc423ec109134319f0a49bd2ecb8
+size 446241
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_a6f4ac2633b6b1d204d5+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_a6f4ac2633b6b1d204d5+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..4886b9e63bf664a3a67a7f5c2f005095f11b1f84
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_a6f4ac2633b6b1d204d5+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d55b306169a3f8df36f04ac17e88eff7a4446f21a768df8406753461cef412f0
+size 43336704
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_b7aecc50b404bc1d53d9+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_b7aecc50b404bc1d53d9+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_b7aecc50b404bc1d53d9+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_b7aecc50b404bc1d53d9+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_b7aecc50b404bc1d53d9+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..c973cdf09f69a5888b45cbe7f77f643b46a340ed
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_b7aecc50b404bc1d53d9+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1188512e2aa967570f1800007a0e10b9f830329a729ebacd835b3bd6aef858bb
+size 333872
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_b7aecc50b404bc1d53d9+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_b7aecc50b404bc1d53d9+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..a15bcf3c4956a4d73de5221af1f2520239949d2f
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_b7aecc50b404bc1d53d9+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe37a0fe785fd25e96a41c2e6d2e36e58e5d0c45e98b46eb9b0b034a5346cca
+size 2376704
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_bb146936ed954dae2a2a+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_bb146936ed954dae2a2a+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_bb146936ed954dae2a2a+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_bb146936ed954dae2a2a+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_bb146936ed954dae2a2a+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..e8901d3de3399351e3047e3a1421477cd9eca40e
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_bb146936ed954dae2a2a+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8e33bea24afec91715003ec36d50782320f951d5bf4c00dab22ef645a0cd72
+size 136998
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_bb146936ed954dae2a2a+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_bb146936ed954dae2a2a+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..5180c07c91e9296f4c08cfde4717a57fd8555bb4
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_bb146936ed954dae2a2a+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_bbe58075930f6345fd2c+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_bbe58075930f6345fd2c+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_bbe58075930f6345fd2c+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_bbe58075930f6345fd2c+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_bbe58075930f6345fd2c+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..eaee94613db6647f1c1896d374fc173917ed33a1
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_bbe58075930f6345fd2c+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b3560d3f5b51f87786d6bea8abc8da69c69875fb8e7ccec34f69cb8274fc5d
+size 46421
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_bbe58075930f6345fd2c+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_bbe58075930f6345fd2c+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..058da1b19639817e88de2a9fc539cea5716d3af7
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_bbe58075930f6345fd2c+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_c22f31e53f4ec2aacb12+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c22f31e53f4ec2aacb12+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c22f31e53f4ec2aacb12+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_c22f31e53f4ec2aacb12+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c22f31e53f4ec2aacb12+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..c7dba559eb31e82df428ef188fab8db3ee54a42a
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c22f31e53f4ec2aacb12+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff3ec6b7a1ec6fac7b9809dbe28bed6213d48b08d8d794b899ab77e21e28ef0
+size 135485
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_c22f31e53f4ec2aacb12+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c22f31e53f4ec2aacb12+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..c2c3e16da425e4179d06613e57e23fd039a0b801
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c22f31e53f4ec2aacb12+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_c5985f85d97aa97e0809+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c5985f85d97aa97e0809+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c5985f85d97aa97e0809+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_c5985f85d97aa97e0809+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c5985f85d97aa97e0809+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..a2896b33e942f4654adf00141ea063226f2b15f2
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c5985f85d97aa97e0809+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4491770e4593f978e89b4240b2d2c137d1a07c439171a4a7d61a03ff72fbe28e
+size 334896
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_c5985f85d97aa97e0809+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c5985f85d97aa97e0809+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..c1269cd790f2ce3bde369ce21a69462f86fe8248
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c5985f85d97aa97e0809+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03cf4a59a8c95767071c477072752f7c171cc16ca5864f9175286fcdb99dcb86
+size 1936384
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_c765d50b5542ffc09176+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c765d50b5542ffc09176+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c765d50b5542ffc09176+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_c765d50b5542ffc09176+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c765d50b5542ffc09176+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..055109c2ca0bb4691382b3830b5c4f502aee848e
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c765d50b5542ffc09176+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e244f8bf4ae9aa7dc8800f833f47866cb97166adf5e6f7037092eb14b4c231a3
+size 334896
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_c765d50b5542ffc09176+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c765d50b5542ffc09176+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..c013b938fecdcdf6fe7f40849afc73857ca79aee
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c765d50b5542ffc09176+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ad682ca78fa76221ffe1c8628f191792b77eb0255849c77d99d781f5254e5b
+size 1455104
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_c7a4a1ee44b16d426dc5+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c7a4a1ee44b16d426dc5+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c7a4a1ee44b16d426dc5+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_c7a4a1ee44b16d426dc5+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c7a4a1ee44b16d426dc5+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..ef9a4936924841875c18481c6eb7ca398522ea83
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c7a4a1ee44b16d426dc5+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c86e083401d6842a3f4c4f429e4ad1887b8e312112265c98f2d44f73d4aaef3
+size 267290
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_c7a4a1ee44b16d426dc5+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c7a4a1ee44b16d426dc5+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..c391658a1911ca1c51a4ac43c00fa8c71cc813b1
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_c7a4a1ee44b16d426dc5+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a990b672ff517f0cbce433d71e70aec32d991f7173417e7ecb620ae711d885
+size 2079744
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_d41951caf693837ced38/config.json b/neuronxcc-2.14.227.0+2d4f85be/MODULE_d41951caf693837ced38/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6fc11f1f5ada714e1911c4b1fa755657b5204e83
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_d41951caf693837ced38/config.json
@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "hf-internal-testing/tiny-random-vit",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 32,
+  "image_size": 30,
+  "initializer_range": 0.02,
+  "intermediate_size": 37,
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "neuron": {
+    "auto_cast": null,
+    "auto_cast_type": null,
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.14.227.0+2d4f85be",
+    "disable_fallback": false,
+    "disable_fast_relayout": false,
+    "dynamic_batch_size": false,
+    "inline_weights_to_neff": true,
+    "input_names": [
+      "pixel_values"
+    ],
+    "model_type": "vit",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_names": [
+      "logits"
+    ],
+    "static_batch_size": 1,
+    "static_image_size": 30,
+    "static_num_channels": 3,
+    "static_patch_size": 2
+  },
+  "num_attention_heads": 4,
+  "num_channels": 3,
+  "num_hidden_layers": 5,
+  "patch_size": 2,
+  "qkv_bias": true,
+  "task": "image-classification",
+  "torchscript": true,
+  "transformers_version": "4.43.2",
+  "vocab_size": {}
+}
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_d41951caf693837ced38/model.neuron b/neuronxcc-2.14.227.0+2d4f85be/MODULE_d41951caf693837ced38/model.neuron
new file mode 100644
index 0000000000000000000000000000000000000000..2184e87665047e6a19a53cd870036ce0f8cdf356
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_d41951caf693837ced38/model.neuron differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_d41951caf693837ced38/preprocessor_config.json b/neuronxcc-2.14.227.0+2d4f85be/MODULE_d41951caf693837ced38/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..41251999692f8249ca3cd5f3cb693c24d3c6f310
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_d41951caf693837ced38/preprocessor_config.json
@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 30,
+    "width": 30
+  }
+}
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_db2224cc81def0c8b21c+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_db2224cc81def0c8b21c+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_db2224cc81def0c8b21c+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_db2224cc81def0c8b21c+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_db2224cc81def0c8b21c+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..3f92b7714f0a36a821df1dc522924f3b9192a6b5
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_db2224cc81def0c8b21c+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9a6a448823a6f02533ce8cf8b2dc5f7cc8679f4b2feec892b6d7f2f01b3879
+size 334896
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_db2224cc81def0c8b21c+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_db2224cc81def0c8b21c+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..a4e3b6a653f410a63a8d6d55e2cfbf3488b1eeac
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_db2224cc81def0c8b21c+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55361a3bec1397217405f4f822515692ac7586905d3cedb465a2621d0f76659
+size 1383424
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_dcd22245b4a305171833+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_dcd22245b4a305171833+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_dcd22245b4a305171833+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_dcd22245b4a305171833+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_dcd22245b4a305171833+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..3d2e6ad21e3e6db17338c0731ca622bedf72d16b
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_dcd22245b4a305171833+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54196855c993aee38498fd94bbd656c85d9097512b5fbcba77ba4ffcbcb4f2e0
+size 361605
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_dcd22245b4a305171833+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_dcd22245b4a305171833+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..06073df3f2032b1c2277f6f34d328fa4a8cb3367
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_dcd22245b4a305171833+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb7ea458578e6e156e92076cb37935d6468e1fd2491ca6679a1fb7a00226fcef
+size 4875264
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_dfbdeb6a41a6733bd817+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_dfbdeb6a41a6733bd817+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_dfbdeb6a41a6733bd817+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_dfbdeb6a41a6733bd817+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_dfbdeb6a41a6733bd817+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..7016faf92e004765e7fdb0e2dcf6dbb33467b9f4
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_dfbdeb6a41a6733bd817+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55fb31fb1ae91ae232c8b1ad2340fbd30d326390287d6c6c41d3db478e286ecd
+size 137155
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_dfbdeb6a41a6733bd817+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_dfbdeb6a41a6733bd817+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..145f2e7857c39df0e4789f8223b0af1e485e294e
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_dfbdeb6a41a6733bd817+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_e28ae2c4e84b1d46a704+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_e28ae2c4e84b1d46a704+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_e28ae2c4e84b1d46a704+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_e28ae2c4e84b1d46a704+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_e28ae2c4e84b1d46a704+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..498218bf20913b7efa3e965a527211a913bc7d1f
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_e28ae2c4e84b1d46a704+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ecdf24f63664247ff76c6599af76ea541c56d695e609fa145b53a4530265f2a
+size 266266
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_e28ae2c4e84b1d46a704+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_e28ae2c4e84b1d46a704+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..5d3855aa4262d14ea5529c00a88a159ac2c4c4f6
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_e28ae2c4e84b1d46a704+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:238c07b42b80b9fe2e1bc8b0578034c1582777a652b1d5623dca3c204e5c1b92
+size 2909184
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_e8582306f63de0ecc01c+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_e8582306f63de0ecc01c+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_e8582306f63de0ecc01c+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_e8582306f63de0ecc01c+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_e8582306f63de0ecc01c+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..a4382b803f93bb948ab4b2a7536feb7a01196175
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_e8582306f63de0ecc01c+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c71bdbab2cebb828bd5be740869264064ab45f4fe5538c2006b560b14fdc5d6
+size 334896
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_e8582306f63de0ecc01c+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_e8582306f63de0ecc01c+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..3b3198f0f629d4052bdf9ca23b28f2c8c10182e0
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_e8582306f63de0ecc01c+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ad9fbba82815f2f205d26914766d06fc3c3a9ff17de4600f2493afab020533
+size 1516544
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_efd89ad55e375daf75e4+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_efd89ad55e375daf75e4+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_efd89ad55e375daf75e4+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_efd89ad55e375daf75e4+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_efd89ad55e375daf75e4+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..1ecd3611357f64a67b0df911e6fea2cb23340f1c
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_efd89ad55e375daf75e4+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057970f211be4530f09edf69a56ef0ff0862f03373975fce6525cdd58e0f3f28
+size 137347
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_efd89ad55e375daf75e4+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_efd89ad55e375daf75e4+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..da23b93c64e9543744f212d57c067c3a4b0fdbe6
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_efd89ad55e375daf75e4+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_f3dfd3986336462d9378+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_f3dfd3986336462d9378+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_f3dfd3986336462d9378+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_f3dfd3986336462d9378+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_f3dfd3986336462d9378+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..61e19e98e093ab0fb9cd896e8faba89942a6d000
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_f3dfd3986336462d9378+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5ad1e1cb35f753c281c15e820196f7d3ebc424d4b9c817cebf6b5fb9ade60d
+size 137347
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_f3dfd3986336462d9378+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_f3dfd3986336462d9378+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..2def4343a2946b162933d100c56d9c8eea70956b
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_f3dfd3986336462d9378+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_f661f6721bb3f19918f8+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_f661f6721bb3f19918f8+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_f661f6721bb3f19918f8+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_f661f6721bb3f19918f8+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_f661f6721bb3f19918f8+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..e68a5a0f1fb58e74de7abc69f96fed52c211f552
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_f661f6721bb3f19918f8+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:683ea82b9a58623c6c4950614371d5d8abd6be263728d1dc8a7cea3ca84a22b2
+size 334896
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_f661f6721bb3f19918f8+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_f661f6721bb3f19918f8+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b8ce624d0ee04d040e722b20f88da35c26a327c0
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_f661f6721bb3f19918f8+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9fcc68126d7ce5fbf31d6ca8a04b3ab18f55b323c85034aa2960a30bc117aed
+size 1659904
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_fa30f35965a9f4fea034+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_fa30f35965a9f4fea034+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_fa30f35965a9f4fea034+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_fa30f35965a9f4fea034+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_fa30f35965a9f4fea034+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..eacf32d97ce23673bb1194da12afc35a8af158f5
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_fa30f35965a9f4fea034+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3651e629bb3e5a2388d505085f2de6d378a0c654b23a3d7afcffaed9b33132d
+size 267290
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_fa30f35965a9f4fea034+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_fa30f35965a9f4fea034+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..32404727a61e90b7469825910bcd47003a319267
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_fa30f35965a9f4fea034+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:621bf7c84ae56c6147870c2b124b7994a3cadb8f1b1f84f76880450fa8a5a26b
+size 1803264
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_fd49a796620925cf3ad0+2c2d707e/compile_flags.txt b/neuronxcc-2.14.227.0+2d4f85be/MODULE_fd49a796620925cf3ad0+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_fd49a796620925cf3ad0+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_fd49a796620925cf3ad0+2c2d707e/model.hlo_module.pb b/neuronxcc-2.14.227.0+2d4f85be/MODULE_fd49a796620925cf3ad0+2c2d707e/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..653a475c9be3adec4713e9e159f8ea3dafaa3027
--- /dev/null
+++ b/neuronxcc-2.14.227.0+2d4f85be/MODULE_fd49a796620925cf3ad0+2c2d707e/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cefdbd2b806647b4e87cc23c850463ef9c8b059d4000d6851c79ff03790f9379
+size 137347
diff --git a/neuronxcc-2.14.227.0+2d4f85be/MODULE_fd49a796620925cf3ad0+2c2d707e/model.neff b/neuronxcc-2.14.227.0+2d4f85be/MODULE_fd49a796620925cf3ad0+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..966c5be6f76b15e4fd1c9ceab8c964bd8c093853
Binary files /dev/null and b/neuronxcc-2.14.227.0+2d4f85be/MODULE_fd49a796620925cf3ad0+2c2d707e/model.neff differ
diff --git a/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/codellama/CodeLlama-7b-Instruct-hf/61b1f78e996f3667f2a3.json b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/codellama/CodeLlama-7b-Instruct-hf/61b1f78e996f3667f2a3.json
new file mode 100644
index 0000000000000000000000000000000000000000..92fda9d9bb61aced509706d310dee9cc9a5928e4
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/codellama/CodeLlama-7b-Instruct-hf/61b1f78e996f3667f2a3.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 16384, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "codellama/CodeLlama-7b-Instruct-hf", "checkpoint_revision": "22cb240e0292b0b5ab4c17ccd97aa3a2f799cbed", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 1000000, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32016}
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-3.2-1B/09c6c17666d478433931.json b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-3.2-1B/09c6c17666d478433931.json
new file mode 100644
index 0000000000000000000000000000000000000000..c426219020e364467877217fdcf3618458472d98
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-3.2-1B/09c6c17666d478433931.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-3.2-1B", "checkpoint_revision": "5d853ed7d16ac794afa8f5c9c7f59f4e9c950954", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 16, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 32.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-3.2-3B/dd3613d57f885e5e99ae.json b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-3.2-3B/dd3613d57f885e5e99ae.json
new file mode 100644
index 0000000000000000000000000000000000000000..f9519acd5e02263f86cdbffb148f8015cf437890
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-3.2-3B/dd3613d57f885e5e99ae.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-3.2-3B", "checkpoint_revision": "43fa890183375f5f69cb9646f29aa99ef3207c22", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 24, "num_hidden_layers": 28, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 32.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/0c6a2750b63f21a1d23b.json b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/0c6a2750b63f21a1d23b.json
new file mode 100644
index 0000000000000000000000000000000000000000..a702bc871899a039035eba006a5a229b25bd9145
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/0c6a2750b63f21a1d23b.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "48d6d0fc4e02fb1269b36940650a1b7233035cbb", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/2370b75ee0c8f8d39cdf.json b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/2370b75ee0c8f8d39cdf.json
new file mode 100644
index 0000000000000000000000000000000000000000..7ad38c733ff69d6f68e6d6aef43f1a191c2ada20
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/2370b75ee0c8f8d39cdf.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "48d6d0fc4e02fb1269b36940650a1b7233035cbb", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/4b3f07d67ca1cb4c7483.json b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/4b3f07d67ca1cb4c7483.json
new file mode 100644
index 0000000000000000000000000000000000000000..746af8683b89957b93732d182fefb755e89b80d8
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/4b3f07d67ca1cb4c7483.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "48d6d0fc4e02fb1269b36940650a1b7233035cbb", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/7ce39f7538e28e682995.json b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/7ce39f7538e28e682995.json
new file mode 100644
index 0000000000000000000000000000000000000000..ea8a6e16f619f6c10e1f83c833b681e1fb50356d
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/7ce39f7538e28e682995.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "48d6d0fc4e02fb1269b36940650a1b7233035cbb", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/bb9f3300fe28df2ac896.json b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/bb9f3300fe28df2ac896.json
new file mode 100644
index 0000000000000000000000000000000000000000..619c9fe7c21f786a6377a562829bbaf519974982
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/bb9f3300fe28df2ac896.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 16, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "48d6d0fc4e02fb1269b36940650a1b7233035cbb", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/mistral/mistralai/Mistral-Small-Instruct-2409/44a01ea18263b02d6b70.json b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/mistral/mistralai/Mistral-Small-Instruct-2409/44a01ea18263b02d6b70.json
new file mode 100644
index 0000000000000000000000000000000000000000..48d525ef092f1fa3add000a92ae64baa9daf0758
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/mistral/mistralai/Mistral-Small-Instruct-2409/44a01ea18263b02d6b70.json
@@ -0,0 +1 @@
+{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 6144, "initializer_range": 0.02, "intermediate_size": 16384, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "mistralai/Mistral-Small-Instruct-2409", "checkpoint_revision": "63e53df6575e7085d62113f4383835ff979b3795", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 12, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 48, "num_hidden_layers": 56, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32768}
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/mistral/mistralai/Mistral-Small-Instruct-2409/88ad7b0405e1f7fb1603.json b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/mistral/mistralai/Mistral-Small-Instruct-2409/88ad7b0405e1f7fb1603.json
new file mode 100644
index 0000000000000000000000000000000000000000..67143fa623db9a46d1c6b883a07a0991d3255e89
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/mistral/mistralai/Mistral-Small-Instruct-2409/88ad7b0405e1f7fb1603.json
@@ -0,0 +1 @@
+{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 6144, "initializer_range": 0.02, "intermediate_size": 16384, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 16, "checkpoint_id": "mistralai/Mistral-Small-Instruct-2409", "checkpoint_revision": "63e53df6575e7085d62113f4383835ff979b3795", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 12, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 48, "num_hidden_layers": 56, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32768}
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/mistral/mistralai/Mistral-Small-Instruct-2409/97e993a84601f66b51a0.json b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/mistral/mistralai/Mistral-Small-Instruct-2409/97e993a84601f66b51a0.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d9594a381f02e60ec4bd246833310eba9a621d0
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/mistral/mistralai/Mistral-Small-Instruct-2409/97e993a84601f66b51a0.json
@@ -0,0 +1 @@
+{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 6144, "initializer_range": 0.02, "intermediate_size": 16384, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "mistralai/Mistral-Small-Instruct-2409", "checkpoint_revision": "63e53df6575e7085d62113f4383835ff979b3795", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 12, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 48, "num_hidden_layers": 56, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32768}
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/mistral/mistralai/Mistral-Small-Instruct-2409/ea6ad7cc51c4f9e5e47b.json b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/mistral/mistralai/Mistral-Small-Instruct-2409/ea6ad7cc51c4f9e5e47b.json
new file mode 100644
index 0000000000000000000000000000000000000000..902427b4a8f05a7ae5980c40b3b2b07986c640e5
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/mistral/mistralai/Mistral-Small-Instruct-2409/ea6ad7cc51c4f9e5e47b.json
@@ -0,0 +1 @@
+{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 6144, "initializer_range": 0.02, "intermediate_size": 16384, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "mistralai/Mistral-Small-Instruct-2409", "checkpoint_revision": "63e53df6575e7085d62113f4383835ff979b3795", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 12, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 48, "num_hidden_layers": 56, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32768}
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_00c2465d32b694cdc75a+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_00c2465d32b694cdc75a+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_00c2465d32b694cdc75a+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_00c2465d32b694cdc75a+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_00c2465d32b694cdc75a+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_00c2465d32b694cdc75a+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_00c2465d32b694cdc75a+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..ba02a671edab3d4d457451bd054983cef605dc84
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_00c2465d32b694cdc75a+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c643532f18abebd61a99bc971cbcf225ba0d7d3f271cd4ea266a2051aabf37c9
+size 128217
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_00c2465d32b694cdc75a+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_00c2465d32b694cdc75a+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..5aec1a2f9b967f3f24f87772c08164dab14c2a2d
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_00c2465d32b694cdc75a+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc79d2f3d623e706d3145eb326a433526573de0874cb1c6bed88011378bc3dd
+size 1393664
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0157f35eb303445e190f+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0157f35eb303445e190f+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0157f35eb303445e190f+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0157f35eb303445e190f+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0157f35eb303445e190f+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0157f35eb303445e190f+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0157f35eb303445e190f+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..2d7695737869d65f4c472eb67be23fa2f937c27f
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0157f35eb303445e190f+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78bda1c787c58a7c91b56f5c7bc8cffba94e94affe25ed93afd5e75f1b41e5ef
+size 263042
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0157f35eb303445e190f+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0157f35eb303445e190f+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..88bf059273c2a2acd27232015f8ec7373ccb65e2
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0157f35eb303445e190f+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adddff966684ab3d8613642345f5a14ed6a9c017076f90fa390503e3ffedf15a
+size 2601984
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_02bf38a18ccb8af02b13+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_02bf38a18ccb8af02b13+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_02bf38a18ccb8af02b13+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_02bf38a18ccb8af02b13+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_02bf38a18ccb8af02b13+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_02bf38a18ccb8af02b13+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_02bf38a18ccb8af02b13+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..e3705a03b8d84b5a195d35070c59525c5ca59a7d
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_02bf38a18ccb8af02b13+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c99aa8fc745db05f72662e0759a9b4e7da44e067388113c5986f603a9a6a292
+size 254241
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_02bf38a18ccb8af02b13+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_02bf38a18ccb8af02b13+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..3333cee747eeb32d3ab017569cd61cbee7d6d5a2
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_02bf38a18ccb8af02b13+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a6c8575d9c7e740b7f41b947b6e6e6cade72f8a3450e7852036d91b273e632b
+size 7916544
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_06636daaadf79562db13+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_06636daaadf79562db13+39f12043/model.neff
index 639a4678dc617fe66ce5c111a3abb2316b47c08f..e24282224b7f832fe81387f4b0a0b03c4a4e3d18 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_06636daaadf79562db13+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_06636daaadf79562db13+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35fc7f5d284a693c5a5f0bce8df9f42bca3fd64ba8896d49b81aa3f3730089b6
+oid sha256:c1728196b501cdc4f3a8fed413033e8bd59c5657976c632f07bc9a2f0d9f915c
 size 13323264
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0a848f64ab3ba788a8a7+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0a848f64ab3ba788a8a7+39f12043/model.neff
index d06b3d2fd51c3525cc2942107f69f56aadeed0e4..8651c1ac08e84f8a852542249ca72a42a65c4d9b 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0a848f64ab3ba788a8a7+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0a848f64ab3ba788a8a7+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35113d20311e06e48af7821452f230daba642da3ecb5ca6b42acad0976bc96a1
+oid sha256:187255cbfc5be1b4d3e82e080b6a91b3a2f3ec586df372fbb60c6ce2f7dec33a
 size 30915584
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0b70f795f32d979dd08f+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0b70f795f32d979dd08f+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0b70f795f32d979dd08f+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0b70f795f32d979dd08f+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0b70f795f32d979dd08f+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0b70f795f32d979dd08f+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0b70f795f32d979dd08f+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..03f913a26251f11423f7b04814c97992ac37d61c
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0b70f795f32d979dd08f+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14231df36f5d3b39032d9b163a7edb288e4a0dab5205866ff8becdb16df14ed1
+size 251010
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0b70f795f32d979dd08f+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0b70f795f32d979dd08f+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..741dd49b6dbccd413448b5e1c3b29a19685b8523
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0b70f795f32d979dd08f+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caaa68f7394524de6e0dc5e70803eabe51d4003caf3aac31fd5daefad5d3d79b
+size 7619584
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0bf56f9a64db27448684+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0bf56f9a64db27448684+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0bf56f9a64db27448684+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0bf56f9a64db27448684+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0bf56f9a64db27448684+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0bf56f9a64db27448684+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0bf56f9a64db27448684+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..b5c703895aad1700b9b14ff7fa483eedabafe87f
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0bf56f9a64db27448684+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:912630a94538c88cbc1614d6884471f20353de7996a0cc45b73c7dbfecadb76c
+size 448637
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0bf56f9a64db27448684+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0bf56f9a64db27448684+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..f5efecd49b785cca83e09cf81ac31176f2f1005c
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0bf56f9a64db27448684+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72457ee96de6c7f3dfd3c81ea4edbeeab2a41f6b596d493ef7b0ef19494df6be
+size 30055424
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0de6c682e356929254c6+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0de6c682e356929254c6+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0de6c682e356929254c6+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0de6c682e356929254c6+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0de6c682e356929254c6+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0de6c682e356929254c6+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0de6c682e356929254c6+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..0cd0ccff5bd09ba6d1e3d535473793a79079beef
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0de6c682e356929254c6+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cdf362c5769d1913f5ffd36ccae43306944d2079126bd1c2f8ee56d220df4bc
+size 290456
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0de6c682e356929254c6+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0de6c682e356929254c6+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..9c152623f38a59f3bb774ca9b39d7f067844061c
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0de6c682e356929254c6+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e5a417c442a64d356a409d4bdd7af7479cb6cf358839a02eecbe2c043ed47d8
+size 3124224
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0eeac286e4dde346cdf4+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0eeac286e4dde346cdf4+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0eeac286e4dde346cdf4+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0eeac286e4dde346cdf4+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0eeac286e4dde346cdf4+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0eeac286e4dde346cdf4+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0eeac286e4dde346cdf4+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..fc41b868167e020066dbd92fb081ba365528dffe
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0eeac286e4dde346cdf4+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257ee8185ed74b915b6c15dccfa4238e96c5026c17e66188704d2bf13e71723f
+size 318032
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_0eeac286e4dde346cdf4+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0eeac286e4dde346cdf4+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..c559461a9f27f3edb6a16dc0394e8dfe75eb8266
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_0eeac286e4dde346cdf4+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db7715990b91e0738a87ef73dbf4b3dddf8e4af61469637826d0001496f94173
+size 8244224
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_107dec43871d718efda8+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_107dec43871d718efda8+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_107dec43871d718efda8+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_107dec43871d718efda8+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_107dec43871d718efda8+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_107dec43871d718efda8+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_107dec43871d718efda8+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..5a7550bd87e45bc5fda061109ef72210e179b07b
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_107dec43871d718efda8+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a10e7c142084c7e9d92b6c4e02bfeabb82f1d15d4c49113a790c53ba10c5f3
+size 455458
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_107dec43871d718efda8+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_107dec43871d718efda8+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..6b11118a6d746f1514ec08900dcaf4755ef940ff
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_107dec43871d718efda8+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed1383f6f24d55e4fc770a1da79bb0bae409acb7edb186b9763a5025283bbb79
+size 27259904
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_127dc040363bce8eb922+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_127dc040363bce8eb922+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_127dc040363bce8eb922+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_127dc040363bce8eb922+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_127dc040363bce8eb922+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_127dc040363bce8eb922+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_127dc040363bce8eb922+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..e50797cbfd68440c9ab17ad94ce6697acc5c2b4d
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_127dc040363bce8eb922+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dee07ef53e70f91fcb3c7db36622d94ebe51d0393e41a44ec33dbc9ba74a0b0
+size 318032
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_127dc040363bce8eb922+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_127dc040363bce8eb922+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..1ea053a3e18e506afc89ed52d20091c95d77b7f0
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_127dc040363bce8eb922+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5181f0f91b558e3bbefea33504e31dc971cb4620c6dcb9e02591ddefe53f29
+size 6687744
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_141ebe85aa9f9d0f05ec+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_141ebe85aa9f9d0f05ec+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_141ebe85aa9f9d0f05ec+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_141ebe85aa9f9d0f05ec+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_141ebe85aa9f9d0f05ec+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_141ebe85aa9f9d0f05ec+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_141ebe85aa9f9d0f05ec+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..f0762dac7f403ff3735717a3876035368519ee09
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_141ebe85aa9f9d0f05ec+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3053533b3dc88abe56e7a3700392bcb2cb308d8721cd726c468ad0fc86c01747
+size 594124
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_141ebe85aa9f9d0f05ec+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_141ebe85aa9f9d0f05ec+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..34e3f66f74e3ce539ad3d300bd7e1c1307d52ad1
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_141ebe85aa9f9d0f05ec+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf7e844b9bc070899c3802302be7d9576f1471ee402e8d304bb156d82c12bf21
+size 9954304
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_1430632f31ac9e097786+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1430632f31ac9e097786+39f12043/model.neff
index 01bb12fb95c2cd7e799531cb938756496aadeccb..a5d57a0a09a859f2a65f17803386ca91fca81492 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_1430632f31ac9e097786+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1430632f31ac9e097786+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cc7512cb9312f1ae581a26a041b2eafc7fe3e2991c7930e9bc760dfd0b77c28
+oid sha256:8b2c2a6ac53c01ba5bbf395c4e9b9a01978706d0b26470006adae8366977583c
 size 30915584
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_15684f4b794e72102d51+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_15684f4b794e72102d51+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_15684f4b794e72102d51+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_15684f4b794e72102d51+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_15684f4b794e72102d51+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_15684f4b794e72102d51+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_15684f4b794e72102d51+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..78726569da503f81d1115609fcf40a3ae27c5c57
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_15684f4b794e72102d51+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56e091f9b252931278aa9dc6003a021700a6fc82daf83fa4195378048a4f2f0
+size 556389
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_15684f4b794e72102d51+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_15684f4b794e72102d51+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..e1889d09f22083d60eaf12903d923fc65aa053e0
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_15684f4b794e72102d51+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0963c70135d9d86eb21bcf038bded03addbe2c6354dafe889dc5f973aae885ad
+size 5121024
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_1948c053c0208cb14f17+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1948c053c0208cb14f17+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1948c053c0208cb14f17+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_1948c053c0208cb14f17+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1948c053c0208cb14f17+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_1948c053c0208cb14f17+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1948c053c0208cb14f17+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..15ece79570e61b2c8ad9d394b5977a69ed64a76b
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1948c053c0208cb14f17+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6f3fda71f2c1b3eed984d364177b44ecd14dc7c7d18b723dc90eb6ef184615
+size 363555
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_1948c053c0208cb14f17+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1948c053c0208cb14f17+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..6d705d2ed796fb1a0e2f5ecf58baa9a8ed3a54f1
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1948c053c0208cb14f17+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ccfd8530eccb0d6e2763d486e34fef189a5331b87c0d7df79057689b77e3e23
+size 5725184
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_1f352aa63d57587fec70+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1f352aa63d57587fec70+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1f352aa63d57587fec70+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_1f352aa63d57587fec70+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1f352aa63d57587fec70+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_1f352aa63d57587fec70+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1f352aa63d57587fec70+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..2cfc12219326df3866d8559071da58f3757b4854
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1f352aa63d57587fec70+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a27818346c81dba9435dd3d4bd63b1336a047edb9003b496b81718ded972bab
+size 128217
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_1f352aa63d57587fec70+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1f352aa63d57587fec70+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..04fff314fe3c225f1e5ba7c51c4d7289abc4e113
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_1f352aa63d57587fec70+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1329618afd3c77310c81523403815b8d8de2736bade82f47c560e391dcb80ec
+size 1721344
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_2004627e11b2e5bd46ba+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_2004627e11b2e5bd46ba+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_2004627e11b2e5bd46ba+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_2004627e11b2e5bd46ba+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_2004627e11b2e5bd46ba+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_2004627e11b2e5bd46ba+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_2004627e11b2e5bd46ba+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..613779cb1800a1552ead99a250277d50a4defb25
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_2004627e11b2e5bd46ba+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0412455284559bd9bb7560e6ae611c50330af4ecfd9752451fed3bec188861b
+size 363555
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_2004627e11b2e5bd46ba+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_2004627e11b2e5bd46ba+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..193c15baf0e1ae5d8e48bf63250dbc0f193ff60f
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_2004627e11b2e5bd46ba+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be3daf7ffe6be6e7cca5433bcc9effd53d4ea925f0760735bdbd80c7354f33d2
+size 4015104
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_216347c7e726ef8144fe+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_216347c7e726ef8144fe+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_216347c7e726ef8144fe+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_216347c7e726ef8144fe+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_216347c7e726ef8144fe+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_216347c7e726ef8144fe+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_216347c7e726ef8144fe+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..131ca9f5afcc91e2645086af1153f100b7627fa9
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_216347c7e726ef8144fe+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de9c50ee6b05cdeb32e6a0ddc01171bca32abac96b7725c1a448ca4ac59095b8
+size 449021
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_216347c7e726ef8144fe+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_216347c7e726ef8144fe+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..0e2ff1d6c5a81f681521c400b9264e45ddf9ae4e
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_216347c7e726ef8144fe+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3611ec9fc51bac6c9c3615614de9047d4363ab690df38dcfa39f438fad4fbc12
+size 30188544
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_21e3dcaee19883fe287e+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_21e3dcaee19883fe287e+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_21e3dcaee19883fe287e+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_21e3dcaee19883fe287e+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_21e3dcaee19883fe287e+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_21e3dcaee19883fe287e+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_21e3dcaee19883fe287e+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..21b87748d94a94ff088cd3fe8abb1c04d2816882
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_21e3dcaee19883fe287e+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c13b522ad45166c5df2d2864c1eb75df2e240879c6db4533b22fec098ee634cf
+size 266465
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_21e3dcaee19883fe287e+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_21e3dcaee19883fe287e+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b7c0cd55af71da7ce0b4c8457becf8e582a726c1
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_21e3dcaee19883fe287e+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ebdacd58ef2217100fd0c38a823a9c96d7be817ae4f2c4f548cb739b6006b0
+size 13323264
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_22991d85a6fe7d79cfb5+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_22991d85a6fe7d79cfb5+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_22991d85a6fe7d79cfb5+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_22991d85a6fe7d79cfb5+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_22991d85a6fe7d79cfb5+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_22991d85a6fe7d79cfb5+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_22991d85a6fe7d79cfb5+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..2f87231ff3a2a93484a3a2304cd9edeed1b153c5
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_22991d85a6fe7d79cfb5+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd85291740379776513f453dbcace08a8fc212945914e9aacbfe9695a6e396f
+size 130974
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_22991d85a6fe7d79cfb5+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_22991d85a6fe7d79cfb5+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..cb7d51600fbf704fe695b4301bb052e40a742ef3
Binary files /dev/null and b/neuronxcc-2.15.128.0+56dc5a86/MODULE_22991d85a6fe7d79cfb5+39f12043/model.neff differ
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_2a756705ae41451bdd91+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_2a756705ae41451bdd91+39f12043/model.neff
index 9ab0c2b8d6d1fe56235fb514b40b81988890bdb4..eb88d4b12ce7ef92bdac41a712082825c5429ac4 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_2a756705ae41451bdd91+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_2a756705ae41451bdd91+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0261389439017a414f93dc0cfab0731999d1e624c437d4d73ae87d3bc0b73e9
+oid sha256:b4c4e01f2e47a17f411f4268a1789a76db7730fc9ecf3285e0683d77086f8d67
 size 6308864
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_2d0ecf614fab08ba3e3a+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_2d0ecf614fab08ba3e3a+39f12043/model.neff
index 0ada59f31a3c1df8b6e47bc8ab59176115040971..dec1ee5c710dd2c083dc18c13dd22bedb2770021 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_2d0ecf614fab08ba3e3a+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_2d0ecf614fab08ba3e3a+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f6bab9ada72287d0dead99fa0374b08cf0ce89a030f6dc028f818dbf78b2fdd
+oid sha256:06781be7b7bd4e9b4986030a6ad677111aa789148b0c67fdc21302b240e6324f
 size 2868224
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_33719efab65aba8971de+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_33719efab65aba8971de+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_33719efab65aba8971de+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_33719efab65aba8971de+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_33719efab65aba8971de+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_33719efab65aba8971de+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_33719efab65aba8971de+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..f0bd73205c778eb4862bc5f171f743d6e5454dac
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_33719efab65aba8971de+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f9714a849abc7a81c860cd24be5de76ad7c037cc74d9c2a225804e0c55e069
+size 266465
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_33719efab65aba8971de+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_33719efab65aba8971de+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b960a98bdaed6cd604b67567b441cf0b8b5a8584
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_33719efab65aba8971de+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed87dde2cdac708657343ed31b729aea5ae6a9fc3962d06900fdcb8d190e91f7
+size 3574784
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_365ac1cdaf18d8317ae6+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_365ac1cdaf18d8317ae6+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_365ac1cdaf18d8317ae6+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_365ac1cdaf18d8317ae6+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_365ac1cdaf18d8317ae6+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_365ac1cdaf18d8317ae6+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_365ac1cdaf18d8317ae6+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..a6916736d2f2d1b5524ea417d687e4ca33b50af1
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_365ac1cdaf18d8317ae6+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8099d176a47d339ed074cafef85701d8b1fc7f717acc907d5fa8e083c8649018
+size 224577
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_365ac1cdaf18d8317ae6+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_365ac1cdaf18d8317ae6+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..d5fec03067334616fa8c28e36bbc29c452a510ec
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_365ac1cdaf18d8317ae6+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b1a2c35a60bbab13bcb4ebf735ac81dfbef0e19bf38659ec2a36c8884166721
+size 3195904
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_37b1814c685ac0d82c92+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_37b1814c685ac0d82c92+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_37b1814c685ac0d82c92+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_37b1814c685ac0d82c92+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_37b1814c685ac0d82c92+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_37b1814c685ac0d82c92+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_37b1814c685ac0d82c92+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..4499344a66c721cbc4b6cfe8bc2383d8e623595e
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_37b1814c685ac0d82c92+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64da8109ab7e4006b9925e0e12e17c421b86fad410ceaf8b5c07b991effe8497
+size 448637
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_37b1814c685ac0d82c92+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_37b1814c685ac0d82c92+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b51ed4b2216e9492fb7942a94a9645bbf25d164d
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_37b1814c685ac0d82c92+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96836bc8fac67010cb48c02f94f98a8a659b33bc57492605ed62034a2e66c970
+size 30055424
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_3c471449bded502e03a7+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3c471449bded502e03a7+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3c471449bded502e03a7+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_3c471449bded502e03a7+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3c471449bded502e03a7+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_3c471449bded502e03a7+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3c471449bded502e03a7+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..e00b03dadb93c34c4ad44c5128da3383f6cf6fb8
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3c471449bded502e03a7+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42984d3532291c02d36869e4cc5a6421e929bed443b21dd3f1f599dec8e50043
+size 556389
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_3c471449bded502e03a7+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3c471449bded502e03a7+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..419c932b65edc3d1712478f778d519c2928eb3de
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3c471449bded502e03a7+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e04d9af3668308803e05c16d4a758e558d09393b30feaff2412861589ee50fa7
+size 5878784
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_3d2012ded37f7e045fe7+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3d2012ded37f7e045fe7+39f12043/model.neff
index eb3b9ccca3c554d9cd4af8d525ecd8de8d21bbd7..9bba881642f231199e5b70f3fd86e8ccc21770b0 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_3d2012ded37f7e045fe7+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3d2012ded37f7e045fe7+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b90a487399d213b25dd3d0c996f4337f4c7f9fb1fa794b0fd448e65270ad9aa
+oid sha256:e25e8c545c049196c1463149cf366c6311f165f5a7fe83924f02d7dd7bb7f727
 size 2253824
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_3f6d05883b6613774923+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3f6d05883b6613774923+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3f6d05883b6613774923+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_3f6d05883b6613774923+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3f6d05883b6613774923+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_3f6d05883b6613774923+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3f6d05883b6613774923+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..bdbdb28afd4746a09c690ef7b236d77a1b7dda9e
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3f6d05883b6613774923+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a88cc2c5cc6b7a3cc184a1d588feb562ad6421ae0d2aa1bc5f0343e463fd2dc2
+size 444642
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_3f6d05883b6613774923+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3f6d05883b6613774923+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b31966e02ba8b3d51401c8dc1535d4685f5ff3f0
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_3f6d05883b6613774923+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33dbfce2035b7e0f49b7b0e30e5be33ac37af41803992e96f561dd133ea54d1d
+size 6411264
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_4164a8ba56c1777c9b02+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_4164a8ba56c1777c9b02+39f12043/model.neff
index d5f60593e5727144eedeb89b4a0301e39b9faf27..da93e17422fc991382a44c32ea80cdf6c5d37a7f 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_4164a8ba56c1777c9b02+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_4164a8ba56c1777c9b02+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d570bc4e896abec3ab0a1daeee20ed83cdc73bcf039666ba88b19eb6204f44
+oid sha256:b5b3876387b5781a6084e0ee1b78e490fe6d60ff3d0078991f87d34c77b0528c
 size 2438144
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_430e78bb7f185201891d+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_430e78bb7f185201891d+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_430e78bb7f185201891d+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_430e78bb7f185201891d+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_430e78bb7f185201891d+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_430e78bb7f185201891d+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_430e78bb7f185201891d+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..7395021355b8a120405e749c34596afbe27e2c2f
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_430e78bb7f185201891d+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f710d61ca7d9a73998c9864583c13407b7f5fc784e249c9ffe6e020aa6d12b8
+size 290456
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_430e78bb7f185201891d+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_430e78bb7f185201891d+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..828e6e2dc3acf1c969b2fb82871ccf726faa4cc4
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_430e78bb7f185201891d+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c261ba8c01c917fd7bef226553cac8dfab8f8cb645e79b7b7cfd1b6a4291b1
+size 3134464
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_458717ec5cd8e550df87+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_458717ec5cd8e550df87+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_458717ec5cd8e550df87+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_458717ec5cd8e550df87+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_458717ec5cd8e550df87+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_458717ec5cd8e550df87+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_458717ec5cd8e550df87+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..6e6f79343b652d1e2858b3238c83b250c3dbefd9
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_458717ec5cd8e550df87+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e47956476dee44b51e3b2da538e41949ae10e11c2bfd98edff4b181298a3020
+size 449021
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_458717ec5cd8e550df87+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_458717ec5cd8e550df87+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..feeab211b50275e934fabc385f8e33ce39ce22c5
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_458717ec5cd8e550df87+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9f89be4264e14216ff008b2cda537eb5bd7e4b5e005ea7cb7c03b2fdbf79ce8
+size 30188544
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_45bedf40dd477066a7fa+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_45bedf40dd477066a7fa+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_45bedf40dd477066a7fa+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_45bedf40dd477066a7fa+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_45bedf40dd477066a7fa+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_45bedf40dd477066a7fa+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_45bedf40dd477066a7fa+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..108ec8b8d93b4874c81b9484233a10ac810bcbd4
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_45bedf40dd477066a7fa+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19bf42cf17bbddd09531675990a46534ebb6812a5cb19b51578104307c05db2a
+size 290456
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_45bedf40dd477066a7fa+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_45bedf40dd477066a7fa+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..bcb9d3237377f349eb2b6519f11fc11a741f1c3e
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_45bedf40dd477066a7fa+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3cff3874fe23bda0fd6146c6360f5f6736bc7cfc725c6c4f05a4b1b28fd532
+size 3175424
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_45e54820556ae91bbc15+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_45e54820556ae91bbc15+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_45e54820556ae91bbc15+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_45e54820556ae91bbc15+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_45e54820556ae91bbc15+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_45e54820556ae91bbc15+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_45e54820556ae91bbc15+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..32b9ae12cf3d3aad5e6fda86b7dca0b988bcad72
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_45e54820556ae91bbc15+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c88d350cd5453bb47b1758f91042cf1200681d997aee9e78bfd65a80df1dd13
+size 130974
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_45e54820556ae91bbc15+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_45e54820556ae91bbc15+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b9b96bb1ad931fd57a9093d15f10af7b1ba13915
Binary files /dev/null and b/neuronxcc-2.15.128.0+56dc5a86/MODULE_45e54820556ae91bbc15+39f12043/model.neff differ
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_479422f85ce1f5ebd67a+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_479422f85ce1f5ebd67a+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_479422f85ce1f5ebd67a+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_479422f85ce1f5ebd67a+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_479422f85ce1f5ebd67a+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_479422f85ce1f5ebd67a+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_479422f85ce1f5ebd67a+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..ed18bd37da0a0b96ccfe22c71529215fc875cd32
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_479422f85ce1f5ebd67a+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d28156ecfa7d5d8fea4deb39a9a3d1d4b180d4926d5f14297606e1dd4e3e7b0
+size 449021
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_479422f85ce1f5ebd67a+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_479422f85ce1f5ebd67a+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..d246a05fc48f9958fb7f00941ae2ab6261110dd3
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_479422f85ce1f5ebd67a+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7efa58b4018892725c7c4d2e67a2e2255615026c2b8cfad9f88b66fba60bfc4f
+size 30188544
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_53ef378f84469d56df4d+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_53ef378f84469d56df4d+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_53ef378f84469d56df4d+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_53ef378f84469d56df4d+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_53ef378f84469d56df4d+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_53ef378f84469d56df4d+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_53ef378f84469d56df4d+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..2a2f7fe4df55b90cda5a1e833d3f0623875f8ec1
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_53ef378f84469d56df4d+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1824a8533188ed969eecdd2bb132e40fc1b18ae5a0524cb2d3f7ba150b50f9f
+size 130974
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_53ef378f84469d56df4d+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_53ef378f84469d56df4d+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..3b4b5bd00c4a1c0f6e48150d20f696d8e1717d86
Binary files /dev/null and b/neuronxcc-2.15.128.0+56dc5a86/MODULE_53ef378f84469d56df4d+39f12043/model.neff differ
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5549dfc1cee1cd892362+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5549dfc1cee1cd892362+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5549dfc1cee1cd892362+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5549dfc1cee1cd892362+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5549dfc1cee1cd892362+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5549dfc1cee1cd892362+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5549dfc1cee1cd892362+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..45c876cdd88b654739fc3c709506bb22ac812af9
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5549dfc1cee1cd892362+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1bf3542e9dce615a2b7cfe27771fe4e03390f6f492f2e5c273d735adfb6810
+size 318032
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5549dfc1cee1cd892362+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5549dfc1cee1cd892362+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..744bbf21d573aefdb6d35df39388d95a2c56176a
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5549dfc1cee1cd892362+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f947d43aa17328e6cc9c4c54d9b26f1d9a020a0a3201995cb3eeaabab3362cb9
+size 7179264
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_580e488b1c902056533c+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_580e488b1c902056533c+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_580e488b1c902056533c+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_580e488b1c902056533c+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_580e488b1c902056533c+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_580e488b1c902056533c+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_580e488b1c902056533c+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..1a3651d4cf1e0b5850a02ef28e167e7918836c00
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_580e488b1c902056533c+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad798cd6193cb8eb8cb423168e9828dbb2778043ebca103c90278cc10cc067b
+size 363555
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_580e488b1c902056533c+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_580e488b1c902056533c+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..ee4648b98ce456320a9c740dcd7b592b2c9e4a2f
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_580e488b1c902056533c+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09662cd7d3c8bb9769326eebc335cda3fd9800ee42e4326fbee8b83a04537f7f
+size 3431424
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_58d0bf37135d5f86b981+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_58d0bf37135d5f86b981+39f12043/model.neff
index b3099f0d6ae6a7a41d1228b164b5ed0665590898..b939ac5f698a0744439e381880944c4e0c58d8b0 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_58d0bf37135d5f86b981+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_58d0bf37135d5f86b981+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b11d61cc30e56b355111b236644e56090e91fdbda597dd440230a506d2d25c7d
+oid sha256:a2157dbc0f334713d2346119d88baa1a51b7dc0f63f4640f35aa9036da0928b4
 size 2448384
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ddb9c233d7c07c4b83e+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ddb9c233d7c07c4b83e+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ddb9c233d7c07c4b83e+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ddb9c233d7c07c4b83e+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ddb9c233d7c07c4b83e+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ddb9c233d7c07c4b83e+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ddb9c233d7c07c4b83e+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..3fc2d522c3445fedee2272e532bebe9176b00c53
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ddb9c233d7c07c4b83e+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cbb50fd1eed63827b775ba3c3c322b3052d1ecc9790ccc89c1209ca7392915f
+size 266465
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ddb9c233d7c07c4b83e+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ddb9c233d7c07c4b83e+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..2b3d8833da27bbab3f488b9d4ca443314075634f
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ddb9c233d7c07c4b83e+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f6dfe62240c09446661a5a76ff5559c3d5d59652eb971362861c438d2ecc46
+size 2479104
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e4c7cfbd9352445f83d+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e4c7cfbd9352445f83d+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e4c7cfbd9352445f83d+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e4c7cfbd9352445f83d+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e4c7cfbd9352445f83d+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e4c7cfbd9352445f83d+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e4c7cfbd9352445f83d+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..7c1cd38ffa3b68c81404a015ba798c140b6856d0
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e4c7cfbd9352445f83d+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0feae3e61a899e2d15cbbae4f31a5f4266f2282397a4b8adf137ac91a5654341
+size 165606
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e4c7cfbd9352445f83d+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e4c7cfbd9352445f83d+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..eeabea4f4bb90e646db38dcb0e1dfe1d9d08004a
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e4c7cfbd9352445f83d+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b9f7d217779bc346bdbd9712938db7a5de0466dac8ca869c2e71648755be80
+size 1567744
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e6dcb3ba87ae7e60d83+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e6dcb3ba87ae7e60d83+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e6dcb3ba87ae7e60d83+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e6dcb3ba87ae7e60d83+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e6dcb3ba87ae7e60d83+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e6dcb3ba87ae7e60d83+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e6dcb3ba87ae7e60d83+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..81654d721421a4c6206b069a6e0750709a9606c9
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e6dcb3ba87ae7e60d83+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:400a6653ccf48c7cf679b7c8e8f0669a42825d637f1d89cd588ab031eb2dea87
+size 165606
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e6dcb3ba87ae7e60d83+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e6dcb3ba87ae7e60d83+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..acda4585178114346425a4e16f8b06b737eccc2a
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5e6dcb3ba87ae7e60d83+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1a0bbfacb168a00ea02575e096c9745790f63c2642875f9c171f058bebb4ae
+size 1362944
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ee3ab5ecb033c6bdeae+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ee3ab5ecb033c6bdeae+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ee3ab5ecb033c6bdeae+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ee3ab5ecb033c6bdeae+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ee3ab5ecb033c6bdeae+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ee3ab5ecb033c6bdeae+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ee3ab5ecb033c6bdeae+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..1b6cbd84f061d6f2a0a4d7da66cf5772d4a38b97
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ee3ab5ecb033c6bdeae+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90bfb0791eca4a22610de235c1f65a77a0eed8f52a74e1642d80374ae28cfbfb
+size 363555
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ee3ab5ecb033c6bdeae+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ee3ab5ecb033c6bdeae+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..e9d46ddcd813fdf536ae6858af93fd0b4466de0b
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5ee3ab5ecb033c6bdeae+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2255c2b3705cea6dc22a327d2f4319920c541a4fe77f50ecdf1c4f63b9f0f7
+size 5735424
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5eefafb0f1f9fc1e59e0+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5eefafb0f1f9fc1e59e0+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5eefafb0f1f9fc1e59e0+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5eefafb0f1f9fc1e59e0+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5eefafb0f1f9fc1e59e0+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5eefafb0f1f9fc1e59e0+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5eefafb0f1f9fc1e59e0+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..72306f15efbea2ca8da6bc517ad31f2b84521a39
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5eefafb0f1f9fc1e59e0+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c07dc29915392d0007ca800aa5b1a69bc855612478157aac287998eb94fad9fc
+size 254241
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_5eefafb0f1f9fc1e59e0+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5eefafb0f1f9fc1e59e0+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..08be8a4fb3c8159dde731781af00c20d5d221e2e
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_5eefafb0f1f9fc1e59e0+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:680c27ca823d452b6c7dbf2cd9b8e609226460bc6296cf4daa357818e57d00bd
+size 7056384
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_633ab94b2d987f84967d+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_633ab94b2d987f84967d+39f12043/model.neff
index 7b0812ddf90436b1d9a24ff63b7c540c3a253b40..e42cb963ee618fa13cb44d47fe7973e0fa7c4ea7 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_633ab94b2d987f84967d+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_633ab94b2d987f84967d+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9060e5f8e557063d9b3fcdf10c8fcbc5102b327a9c911bd697646598acf2bcff
+oid sha256:52c8aa8ab4600ff102589eb1841a9893fe5d50189649503b2836b7965bb7b2fa
 size 2458624
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_63e06f8c133abeece2ff+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_63e06f8c133abeece2ff+39f12043/model.neff
index 0997fe810d8a48d6d6fdffec67be35ae180f3794..cbd5e7d4f8b77faa9665661e1a3a0a733b3876ba 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_63e06f8c133abeece2ff+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_63e06f8c133abeece2ff+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e20b22770a4141f1e66923348271bc1ed2ec457b6769f007cef033b7e7ff7f
+oid sha256:a1444e31fbeeb300b0abcb5087e9cb672ed0c8fc5ad4e90e79fb27c23b937ffb
 size 2345984
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_677971d7856e73f86fd8+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_677971d7856e73f86fd8+39f12043/model.neff
index db195706b5f77e45304d61e29585ce580fbb5a30..fc19dca56429dccbd10e7477f9c5dab4b74f5ff4 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_677971d7856e73f86fd8+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_677971d7856e73f86fd8+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6965a1898c6de6d4cf0dbaa64edc191784bc2e80b4186ff4c8eacad0ca355f2
+oid sha256:f7e351be3f40853d159e28b84660c8c1039a3a7fd493e86ee37e2e1ad349cb4d
 size 2243584
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_6d6c15e58725fa158325+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_6d6c15e58725fa158325+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_6d6c15e58725fa158325+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_6d6c15e58725fa158325+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_6d6c15e58725fa158325+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_6d6c15e58725fa158325+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_6d6c15e58725fa158325+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..f9a3a290d8d4470d779c712be7c306e1e7840211
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_6d6c15e58725fa158325+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d151b2a6d3825ed2bf67c2c2d0c0bb30f174900cc7fd1c16612d1756d1777e
+size 128217
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_6d6c15e58725fa158325+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_6d6c15e58725fa158325+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..f884b36b0bfd8f686cf9489eeab8b51c14ed7912
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_6d6c15e58725fa158325+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8332009119d2a0deaeef38853563970635f59eea25abe888c3c8d4b3537ed1a4
+size 4250624
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_703336702854a488dfa4+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_703336702854a488dfa4+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_703336702854a488dfa4+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_703336702854a488dfa4+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_703336702854a488dfa4+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_703336702854a488dfa4+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_703336702854a488dfa4+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..6bfe404fbb90d076bb8c5993ee1e0f3a77e59001
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_703336702854a488dfa4+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e18d1ab28c34a554ee6d56b941a4f04c34f3c27ec132746b968bccd31b1eeb
+size 254241
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_703336702854a488dfa4+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_703336702854a488dfa4+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..da3e12bf999230207f0f1f0a47735be8ee5b5cf3
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_703336702854a488dfa4+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bd5c726deff8fbb44907ebcb5dc0c96d0dca109f6e515785dc4b7ca38816e1d
+size 10333184
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7661d6eadbe802c530f4+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7661d6eadbe802c530f4+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7661d6eadbe802c530f4+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7661d6eadbe802c530f4+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7661d6eadbe802c530f4+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7661d6eadbe802c530f4+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7661d6eadbe802c530f4+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..9709eccf8566af7722ecdf680de588ba0f8a1455
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7661d6eadbe802c530f4+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5031ce5af1fbcfb02fa89416c59d5faa2dbf4650fa204fb6715fd9ac2152decf
+size 444642
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7661d6eadbe802c530f4+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7661d6eadbe802c530f4+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..1472dc1dc3e3b4748c349d2c0b1c0f5561a98a59
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7661d6eadbe802c530f4+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c4d75625082a53bd5fff18d87ef66b96107cd97aad049ac1af66d3d08041d9a
+size 1229824
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7719ec8fd597806cec35+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7719ec8fd597806cec35+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7719ec8fd597806cec35+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7719ec8fd597806cec35+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7719ec8fd597806cec35+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7719ec8fd597806cec35+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7719ec8fd597806cec35+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..5b102caeb40834f9c0283dc3f63f19c37ce587c7
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7719ec8fd597806cec35+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f66baeb8671ca0414047441201687c831b42a945813bce0a3fb2099f9f2fc3
+size 363555
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7719ec8fd597806cec35+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7719ec8fd597806cec35+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..4b5ffd29d9673b5d32daa6b19427e616c2d53583
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7719ec8fd597806cec35+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceba986016f72a493cb9b14c80c4dbc9bdbfe46c4155fd492cd93cd8a36ab9fc
+size 3113984
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_77f52b3bc8e641473aab+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_77f52b3bc8e641473aab+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_77f52b3bc8e641473aab+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_77f52b3bc8e641473aab+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_77f52b3bc8e641473aab+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_77f52b3bc8e641473aab+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_77f52b3bc8e641473aab+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..523c3ef42d2821ecf1bc2239a1e5238956454624
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_77f52b3bc8e641473aab+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e1b6b2f786e3fa4c37adedba5d752a1330d296e13222fbbc65d2552df1185f4
+size 444642
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_77f52b3bc8e641473aab+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_77f52b3bc8e641473aab+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..7afd70a7ad3b73724996dbec7feb169f73d76c62
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_77f52b3bc8e641473aab+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cfb9526faf94c0d710aad9cbeb2537b54f039963e6a1c9e4241709075098d43
+size 5807104
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_79389d88c33464914847+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_79389d88c33464914847+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_79389d88c33464914847+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_79389d88c33464914847+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_79389d88c33464914847+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_79389d88c33464914847+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_79389d88c33464914847+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..00ea49ac7ba77cb024cb48f92c681548d5d47b2b
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_79389d88c33464914847+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9d3570e14d6af8d5800db785e8c09a7e8ed2d4ba6f8868491a52766b9b07651
+size 290456
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_79389d88c33464914847+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_79389d88c33464914847+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..e9a5421034432fe353f839e50dbebb2fd5b63376
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_79389d88c33464914847+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efe693d97de986d88c89c935cb001716f4046bc863c649ea9032c8aaae0ac304
+size 3277824
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7a5881d8f3cfc70fe0d7+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7a5881d8f3cfc70fe0d7+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7a5881d8f3cfc70fe0d7+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7a5881d8f3cfc70fe0d7+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7a5881d8f3cfc70fe0d7+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7a5881d8f3cfc70fe0d7+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7a5881d8f3cfc70fe0d7+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..1f621df0be364b8a3cd27d186bac12e6bb510925
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7a5881d8f3cfc70fe0d7+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ae863345176801bd306e2ed9b0251f65cb25437612dd2531746e8af8a370c31
+size 449021
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7a5881d8f3cfc70fe0d7+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7a5881d8f3cfc70fe0d7+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..fdb819d32693ca77127268df08599699f7fb6eaa
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7a5881d8f3cfc70fe0d7+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf18da0000671c8c745441cb8fc3ba6441d44d7f30d98081ed20fe345fff0bb6
+size 30188544
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7c0801da95a6c1ed7e30+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7c0801da95a6c1ed7e30+39f12043/model.neff
index 87fa75fe448cfb91ac1bf82b5b9af500b06c06e9..11ee2665b7dcef7103d16a42e6005fe8ff360fd6 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7c0801da95a6c1ed7e30+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7c0801da95a6c1ed7e30+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2927da8f9b89e2a0fa1fdec3fbe43c4c238d97e32ea0fcd00de5704dad1ca100
+oid sha256:af259beabf75b807e7e32529ca26522eed262a8641eee56b6f0d12181cb3f27e
 size 30915584
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7c94578e80247ad042b9+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7c94578e80247ad042b9+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7c94578e80247ad042b9+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7c94578e80247ad042b9+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7c94578e80247ad042b9+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7c94578e80247ad042b9+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7c94578e80247ad042b9+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..abb3b6a0851e6d3b94195b147c29e462ce225b71
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7c94578e80247ad042b9+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76825bcb5b5c82ed775fe63f4f3e1a677d503c07e551b4dcdfe91127c1bc0b7
+size 455458
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_7c94578e80247ad042b9+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7c94578e80247ad042b9+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..2c67385b76a287ba89a12cd6c7835c5bb18e1317
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_7c94578e80247ad042b9+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e21e5f55216e16abd04de8956084d6c80cad03109eadd1e5a52790f981da41ee
+size 27259904
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_80adfd88e3f30235a817+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_80adfd88e3f30235a817+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_80adfd88e3f30235a817+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_80adfd88e3f30235a817+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_80adfd88e3f30235a817+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_80adfd88e3f30235a817+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_80adfd88e3f30235a817+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..070e97d8c154ee11a3b47c0ba26d13cc424703c3
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_80adfd88e3f30235a817+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df36a8df523f0490a83df215bb3a0a4c0c4450e26fe7fdd1450da73582cd9655
+size 556389
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_80adfd88e3f30235a817+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_80adfd88e3f30235a817+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..ebbda59964cb4e471382736169e8fcada7125ae5
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_80adfd88e3f30235a817+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f244150966269a4c6395c464db09caf2fbfab8d6ba01b760bf6d05eb88b8cf9
+size 5172224
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_83867e44a27b65a12481+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_83867e44a27b65a12481+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_83867e44a27b65a12481+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_83867e44a27b65a12481+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_83867e44a27b65a12481+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_83867e44a27b65a12481+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_83867e44a27b65a12481+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..03c2f4556fe717775eca0a246ba4b3d95c37a879
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_83867e44a27b65a12481+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:531ffd4ed8b79712eb036c11d772de876bdc2c14510a611f8293ad74a8568a38
+size 594124
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_83867e44a27b65a12481+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_83867e44a27b65a12481+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..64e12f82a5aaa5c7ae641093d77a4bfa17a04711
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_83867e44a27b65a12481+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42ae73cb69132d49a02f252f554dca866a83a9469e896e715b7df6677f45d303
+size 7588864
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_866bbf0d17b9db9b493d+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_866bbf0d17b9db9b493d+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_866bbf0d17b9db9b493d+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_866bbf0d17b9db9b493d+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_866bbf0d17b9db9b493d+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_866bbf0d17b9db9b493d+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_866bbf0d17b9db9b493d+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..e3742de2fc8cbf13344ec534471c3b2a73b1b430
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_866bbf0d17b9db9b493d+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a53fef2c5b61e035a9133cdc531d7bde31548f38ab70357d8bf877935ac0af25
+size 363555
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_866bbf0d17b9db9b493d+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_866bbf0d17b9db9b493d+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..78da9cf8be6917c4040af6d18e8653a6fa45d2d2
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_866bbf0d17b9db9b493d+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4023815f8e2e8cdf4c6394af64f5e2b4a0915283b33cb31a2eacf1ded3d7bba7
+size 4015104
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_87bca61b0e0d50c81990+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_87bca61b0e0d50c81990+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_87bca61b0e0d50c81990+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_87bca61b0e0d50c81990+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_87bca61b0e0d50c81990+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_87bca61b0e0d50c81990+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_87bca61b0e0d50c81990+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..afdd140849ea7d89e5d1f91236e827eb03441607
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_87bca61b0e0d50c81990+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c66a0b551541333d2dbde45fd6cecea14ec5dd45b64ee3308e9099991ca0572
+size 455458
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_87bca61b0e0d50c81990+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_87bca61b0e0d50c81990+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..6d1814f5cbd077974d2fe75a2e42630ca953af17
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_87bca61b0e0d50c81990+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c95be4a12e84dd734b0378c11503ab6ccf7d59fd34cd44fe55ddc26e234cd5bf
+size 27259904
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_8bdb334c1899e9bed2c5+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_8bdb334c1899e9bed2c5+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_8bdb334c1899e9bed2c5+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_8bdb334c1899e9bed2c5+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_8bdb334c1899e9bed2c5+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_8bdb334c1899e9bed2c5+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_8bdb334c1899e9bed2c5+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..44569fb91e7b1eedd97c77e9d1c579a6c6d24d87
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_8bdb334c1899e9bed2c5+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77e8b4f5e2840c2d23e6dfe8f0c7eb82114d4412c4083151826b4781c6d2cf8
+size 507443
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_8bdb334c1899e9bed2c5+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_8bdb334c1899e9bed2c5+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..c0d21e7d68c589e8231f903b6ffcff2050f5ce89
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_8bdb334c1899e9bed2c5+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a41907b8477d818243687bdb171142eb60d734aac1fa1126a741e45b1b4d8d
+size 2960384
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_967b0f433d458fa4e23d+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_967b0f433d458fa4e23d+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_967b0f433d458fa4e23d+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_967b0f433d458fa4e23d+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_967b0f433d458fa4e23d+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_967b0f433d458fa4e23d+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_967b0f433d458fa4e23d+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..74713ca07b30c32c2abb35b56cd02c6f7a88964d
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_967b0f433d458fa4e23d+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5744a60a4c832aadc52c270788e1698c3851ada55aa35a4f59b5f68b1d0cd562
+size 363555
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_967b0f433d458fa4e23d+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_967b0f433d458fa4e23d+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..3e0ebe768eb56829e02131d26a7941927f1c8757
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_967b0f433d458fa4e23d+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab7775c6e98f7a39b725161105a066658ad779fbbf5f211d199b14b84f84f9e
+size 3421184
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_987d0c49976db779c28a+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_987d0c49976db779c28a+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_987d0c49976db779c28a+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_987d0c49976db779c28a+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_987d0c49976db779c28a+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_987d0c49976db779c28a+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_987d0c49976db779c28a+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..74685c76a2e0af4bb0c6229e3473977ae387f545
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_987d0c49976db779c28a+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdca5484e0046205e3be6b9e02d2a905152e5f597be7ece0192a1a61789eeb11
+size 130974
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_987d0c49976db779c28a+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_987d0c49976db779c28a+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..4adcde69489e68b07de96b8b6bec4a918c007a60
Binary files /dev/null and b/neuronxcc-2.15.128.0+56dc5a86/MODULE_987d0c49976db779c28a+39f12043/model.neff differ
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_99a69aadae08714e73ed+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_99a69aadae08714e73ed+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_99a69aadae08714e73ed+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_99a69aadae08714e73ed+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_99a69aadae08714e73ed+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_99a69aadae08714e73ed+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_99a69aadae08714e73ed+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..8e18ae135d3491860571dcfcf7f0256631c7e52c
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_99a69aadae08714e73ed+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b98de418adfeaf643e73a4ff90c53c3dab755d38995f579e89a109567250dbe
+size 444642
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_99a69aadae08714e73ed+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_99a69aadae08714e73ed+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..561e3eef2ca487d59bea9f1840de20ba5db68bc1
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_99a69aadae08714e73ed+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fa97301c946f79fbcf608f3871819af05538a4f0a305064a593262cc6f9acee
+size 8428544
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_9ac5df1af559151d7b88+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_9ac5df1af559151d7b88+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_9ac5df1af559151d7b88+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_9ac5df1af559151d7b88+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_9ac5df1af559151d7b88+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_9ac5df1af559151d7b88+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_9ac5df1af559151d7b88+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..dd6bedc0a827687375de172cd0bd43d1985d139d
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_9ac5df1af559151d7b88+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dff2da13e88fe8cff6459165199d958a2822b1f5618157a59e618b649f924c15
+size 507443
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_9ac5df1af559151d7b88+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_9ac5df1af559151d7b88+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..c12ef8bcd2486d4fa510626b97d195034c69fbe4
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_9ac5df1af559151d7b88+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf5a08eac6433988e9919fee42ba7733f163bbfcdd5c2c286e1766ac1e82e8a1
+size 2960384
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_9b0eecb5e0b590f9420a+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_9b0eecb5e0b590f9420a+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_9b0eecb5e0b590f9420a+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_9b0eecb5e0b590f9420a+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_9b0eecb5e0b590f9420a+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_9b0eecb5e0b590f9420a+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_9b0eecb5e0b590f9420a+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..123566fbd147449e4c1f421bcca418067789bfc4
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_9b0eecb5e0b590f9420a+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2510f9dabb6ff2ff1bd53450999d914328967ca43e6c0ea9c02366c8a2468c61
+size 290456
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_9b0eecb5e0b590f9420a+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_9b0eecb5e0b590f9420a+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..44225ffb4d0986b374bd1813f55c43fba0887524
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_9b0eecb5e0b590f9420a+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d4f723d09be523219ba2658fa17b9c8c5f0c5f0ea016de2012f7f86c4fb5b76
+size 3462144
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a07a000f4aa986d9fd28+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a07a000f4aa986d9fd28+39f12043/model.neff
index 8304a504eb16763ac06f213a9515c1edaabbcf1e..a07e3b75d1cead93f004e21f47e891b55a23a1b6 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a07a000f4aa986d9fd28+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a07a000f4aa986d9fd28+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02528634466ea377e97a823846cef141f794ace07c9fcc73e5beb0817c0119b9
+oid sha256:7d9f20ab196c2d68013816f5e96bb5173d1429a7a4c8b81d11f0ed4cf7944dbb
 size 2253824
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a0a5efc77c5084df68b7+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a0a5efc77c5084df68b7+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a0a5efc77c5084df68b7+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a0a5efc77c5084df68b7+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a0a5efc77c5084df68b7+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a0a5efc77c5084df68b7+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a0a5efc77c5084df68b7+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..3c7e6011b8f07cd6112505fab58f0619221f6839
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a0a5efc77c5084df68b7+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd0aa3127c90456b01b544e126ac097ed9d8b196196636c08d71b5f58d482b5b
+size 318032
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a0a5efc77c5084df68b7+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a0a5efc77c5084df68b7+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..148bbd35b89780303c8141f2edb29cea903a50e8
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a0a5efc77c5084df68b7+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93e6651c837c61d671037b0acdaa4fa7b1839a39c4b02e3fcb9ef7afdb9ee21
+size 6278144
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a140efb3351c8d199e2c+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a140efb3351c8d199e2c+39f12043/model.neff
index 98a77c83e080702f3afa955afaf451c821ed01b4..8191376a75e6814105c1fe1e2e791f16add7024b 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a140efb3351c8d199e2c+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a140efb3351c8d199e2c+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6208cc9cd6232ba3ec3317012e8117541c41c694fbc0f2dca2e7d29702a60057
+oid sha256:ee218275a3908eb611328c9abb6927c72c01fe584ceeedc09673a381d0c91881
 size 2305024
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a3426cf68b987d331b3c+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a3426cf68b987d331b3c+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a3426cf68b987d331b3c+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a3426cf68b987d331b3c+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a3426cf68b987d331b3c+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a3426cf68b987d331b3c+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a3426cf68b987d331b3c+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..c2dae64d2a2b092ebe1beedb9529aeabf0c46bcd
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a3426cf68b987d331b3c+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49e13db3a5cab5c3b0657d2d86293479d2fe9ccebb907b680a470b59d355bd02
+size 455458
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a3426cf68b987d331b3c+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a3426cf68b987d331b3c+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..19d7639bba01b9e687257e6e6ff0bda9bd6eda66
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a3426cf68b987d331b3c+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2956496417f830d087ee60c816700ff4728aaf7000d7aed45dee3cc160f33f7e
+size 27259904
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a4f3f00fbd1b3e7a58a6+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a4f3f00fbd1b3e7a58a6+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a4f3f00fbd1b3e7a58a6+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a4f3f00fbd1b3e7a58a6+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a4f3f00fbd1b3e7a58a6+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a4f3f00fbd1b3e7a58a6+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a4f3f00fbd1b3e7a58a6+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..d9cc9213a4c391bb31ce4122fc296e1a4b751d72
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a4f3f00fbd1b3e7a58a6+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed580d22fe056eb8c8a773cbd6ea816ee65c3244cb1e20f4a73c384c20c5dcc
+size 594124
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a4f3f00fbd1b3e7a58a6+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a4f3f00fbd1b3e7a58a6+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..e2f22eb63b8fe976373bab24216103db65adccbc
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a4f3f00fbd1b3e7a58a6+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3af8349ff00854ceb858461e6a5f17a40d41ed09184bd81916659469f48fcd
+size 14029824
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a99da8b7c6d00f75a130+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a99da8b7c6d00f75a130+39f12043/model.neff
index 2b4a9f53762d9347ea0389a8c3834a6fbe7cc53b..9c9788ace4fc2e18419c5ad3e15f96dcbbf6ef26 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_a99da8b7c6d00f75a130+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_a99da8b7c6d00f75a130+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e8e4a03286320a4630ae626d43bba99dbaf742c87b6bd2bdb9e1535b656bb8
+oid sha256:547129c0611ebd5733a7d7ceee2af4d2823a1fae5d4141eddaef44cdc38f8f3e
 size 2274304
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_aaeee402a55cb205f6f8+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_aaeee402a55cb205f6f8+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_aaeee402a55cb205f6f8+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_aaeee402a55cb205f6f8+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_aaeee402a55cb205f6f8+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_aaeee402a55cb205f6f8+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_aaeee402a55cb205f6f8+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..5238f5ad4feda36fe2ebb1099e15ab7853f126ac
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_aaeee402a55cb205f6f8+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa9d07394631aad607cd316df944f76dfce0a2e821a32a7eba75e606dea6f4a7
+size 507443
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_aaeee402a55cb205f6f8+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_aaeee402a55cb205f6f8+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..fea3dc66a9f3992f9146006a0cbbc499368f1516
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_aaeee402a55cb205f6f8+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2877a433c0ba1961a04ad3f4c9bb45ae880b70bb366a427425e157e424067790
+size 2960384
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b01949283e27a04f0e6e+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b01949283e27a04f0e6e+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b01949283e27a04f0e6e+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b01949283e27a04f0e6e+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b01949283e27a04f0e6e+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b01949283e27a04f0e6e+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b01949283e27a04f0e6e+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..cd1df83e653b2aa99eb5c19419c7a48da75ac012
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b01949283e27a04f0e6e+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807594f96ac8dce25d1b42c48f6a3aa4c2b5ebe408ffc875a9eb78b06cae2d30
+size 224577
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b01949283e27a04f0e6e+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b01949283e27a04f0e6e+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..2e6d07beb58ff38457fc51a016808cf3efea7a87
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b01949283e27a04f0e6e+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b7110e478a676febb3b64b9bb7ec78d82ad4190a1794854e4526c9e622b4669
+size 4588544
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b6f31af295bc1fdd0707+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b6f31af295bc1fdd0707+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b6f31af295bc1fdd0707+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b6f31af295bc1fdd0707+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b6f31af295bc1fdd0707+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b6f31af295bc1fdd0707+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b6f31af295bc1fdd0707+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..2db0e33e9646f8855945514eaf01fc515e939b90
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b6f31af295bc1fdd0707+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aff3046371659038a92593b0a9b98231563ca8be4cf9e57fae8e1d513ecc578
+size 556389
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b6f31af295bc1fdd0707+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b6f31af295bc1fdd0707+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..01e86141f30a4f82a8251220f8341133cf178008
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b6f31af295bc1fdd0707+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f3fc3678d09f0eda824eb3ad6db77a4ff207dd13e2bdc3c2f049db5e806bc2
+size 5284864
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b720c31dac82c34258cd+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b720c31dac82c34258cd+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b720c31dac82c34258cd+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b720c31dac82c34258cd+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b720c31dac82c34258cd+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b720c31dac82c34258cd+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b720c31dac82c34258cd+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..c1c5b3e5a8c438e0a585e92542624dd37659ad09
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b720c31dac82c34258cd+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73da359b09095ca00b0e1e92f0fb5536725e9ed0326a947b434f61bc3e911032
+size 318032
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b720c31dac82c34258cd+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b720c31dac82c34258cd+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..f469a44e8da8c6928ddcc7f305f7f0c7849b0347
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b720c31dac82c34258cd+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8ece4d7b7753bdd3874884358327cdd227801ca67324a151851d6d22ce1c40
+size 6206464
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b73835229038eafd2762+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b73835229038eafd2762+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b73835229038eafd2762+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b73835229038eafd2762+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b73835229038eafd2762+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b73835229038eafd2762+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b73835229038eafd2762+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..df86b0126c46348bed4ea97d1f7df8ef0c0ef544
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b73835229038eafd2762+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a78f373adffeb900f0631b9c3636d8890872a163c2919fe1dbd6a59f14752e34
+size 165606
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_b73835229038eafd2762+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b73835229038eafd2762+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..0ef23fbcf82853b56c3e0937a1db1eeddf2928fe
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_b73835229038eafd2762+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61029f109d3531fc4e935ed8b946938b73bd28e2feb4aa845dc9d8db2d7eac57
+size 1373184
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_bbf8f266dde11f6232c8+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_bbf8f266dde11f6232c8+39f12043/model.neff
index 23d6fbb01cf3eddccc0faa15444269d6280a71a9..f2dcb6eaa8b83367aa97f96449df15ecdcd43336 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_bbf8f266dde11f6232c8+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_bbf8f266dde11f6232c8+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5a4b01382e142d3247ddcde105ec905240575937e083191e39c5b2a7f4ad06
+oid sha256:4badecc30b5865e2e2abd2fb85187c6e880f5d5d9b2c1bc9218f4584fd4e5217
 size 2243584
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_bc1e7bba65773bae73fb+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_bc1e7bba65773bae73fb+39f12043/model.neff
index 164f65357057bc15fdca6dbf3d8ccc2e81bd92ad..fe43ccd1fbc5e57c57ee191ab311a4532a16b8d5 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_bc1e7bba65773bae73fb+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_bc1e7bba65773bae73fb+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0781500219069ebd140b52eafdafa605bf095bd4f9852855670c004fb2a0970
+oid sha256:e6c5e0f8e9fab419800b28de8b6f129976e94949ebd77f368120129d2fee9b8e
 size 2345984
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_bdf4f86a85b75038b651+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_bdf4f86a85b75038b651+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_bdf4f86a85b75038b651+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_bdf4f86a85b75038b651+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_bdf4f86a85b75038b651+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_bdf4f86a85b75038b651+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_bdf4f86a85b75038b651+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..b9f4568d00159781fa7bd3218ba159278da108b1
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_bdf4f86a85b75038b651+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73667864573c4d2ce2eb558985cf084b4031e46d43a33b865a92f7468ef64d5e
+size 165606
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_bdf4f86a85b75038b651+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_bdf4f86a85b75038b651+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..ac23de2d359fab7e9cf60b406f2a7f0f4ee558d8
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_bdf4f86a85b75038b651+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd725b233e1259661a3c58e964d4755c74e4e40c20110ec666bf35e7fffdf92
+size 1403904
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_be4df199a79b7377e53a+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_be4df199a79b7377e53a+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_be4df199a79b7377e53a+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_be4df199a79b7377e53a+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_be4df199a79b7377e53a+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_be4df199a79b7377e53a+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_be4df199a79b7377e53a+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..3f693068a2f9ddab4564b88449038f8b1475a403
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_be4df199a79b7377e53a+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df5a88a7317766c96476d97258b62a6826c3bb1039226c14ee42d8b8783cef63
+size 128217
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_be4df199a79b7377e53a+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_be4df199a79b7377e53a+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..50001e667ad9498fe74cca91fcf1af18873a5173
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_be4df199a79b7377e53a+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df3ba8672cb9476f56b490f8ea89836dda99fca113749e97ef2bf7f4ba13604d
+size 10005504
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c3e577073bafae1e671b+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c3e577073bafae1e671b+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c3e577073bafae1e671b+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c3e577073bafae1e671b+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c3e577073bafae1e671b+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c3e577073bafae1e671b+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c3e577073bafae1e671b+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..1298c436498bb9a6626f1bc0950ea3899446e3ce
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c3e577073bafae1e671b+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc596b865a3cc75ea2a857277f6b59bedeb44eda760e16d6cfb8deffef677eee
+size 224577
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c3e577073bafae1e671b+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c3e577073bafae1e671b+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..6251bd184a21d3fca90d6b69d7054b9104c2cdae
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c3e577073bafae1e671b+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c060ec9141d9276e9021b7b2356bedca76d7c9f2bd873bee8cf63f9b3f07fd4
+size 20798464
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c4a2455c5b25dada65d7+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c4a2455c5b25dada65d7+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c4a2455c5b25dada65d7+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c4a2455c5b25dada65d7+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c4a2455c5b25dada65d7+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c4a2455c5b25dada65d7+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c4a2455c5b25dada65d7+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..deb740af46884d8564e0999eba673b0e058ed86d
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c4a2455c5b25dada65d7+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc5ee238b4dd97a5434accedd8c60362714a2810e971338d42f4e2c4ab05311
+size 224577
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c4a2455c5b25dada65d7+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c4a2455c5b25dada65d7+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..255cb09c172ec75a97c89c09f758d5fe1a04c528
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c4a2455c5b25dada65d7+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1631ef3fa7677c8e7c7290f79def6f79709e85634529d556d31d0718371180db
+size 9923584
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c548cc651b8f6e85d9e8+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c548cc651b8f6e85d9e8+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c548cc651b8f6e85d9e8+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c548cc651b8f6e85d9e8+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c548cc651b8f6e85d9e8+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c548cc651b8f6e85d9e8+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c548cc651b8f6e85d9e8+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..2a8a15619bf3381a4943ec8bc80aafaf8772ba1a
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c548cc651b8f6e85d9e8+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ae8778cd85b64bca8f06e3d9f078b9cdfc2510510da75045fdaf5955c1b96bc
+size 221466
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c548cc651b8f6e85d9e8+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c548cc651b8f6e85d9e8+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..6348ba791ff8cbd76301bcd632e6b1d9d688088b
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c548cc651b8f6e85d9e8+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:014b086c504bfcce9682531bcc0b0b22831485f2f603fb834c83e98d733c1566
+size 3697664
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c57f19ed333f0e818ff9+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c57f19ed333f0e818ff9+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c57f19ed333f0e818ff9+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c57f19ed333f0e818ff9+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c57f19ed333f0e818ff9+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c57f19ed333f0e818ff9+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c57f19ed333f0e818ff9+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..1a833e948b9b51d3e27638023167a4d9d0b6ca64
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c57f19ed333f0e818ff9+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52fbd8e4319bbc25c1b909ea054d1729c25a82e162839e5241f3ed8f1227f7d4
+size 556389
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c57f19ed333f0e818ff9+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c57f19ed333f0e818ff9+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..102be3bff07763f8605dfda1cba8fcc5fbc193b7
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c57f19ed333f0e818ff9+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65b877de88066721280d805ff9cfe375dc2c5009932ca6cfcc52228f903e3b2a
+size 5489664
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c65426c729b86309e34a+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c65426c729b86309e34a+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c65426c729b86309e34a+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c65426c729b86309e34a+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c65426c729b86309e34a+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c65426c729b86309e34a+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c65426c729b86309e34a+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..5940a2e4bc10ccee2aa32b7d0fbae9bc5a413502
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c65426c729b86309e34a+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:869d43804432deadb053157bcedd3c8eb600afed45edad3196c8cd55224203f0
+size 439011
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c65426c729b86309e34a+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c65426c729b86309e34a+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b2c959ff113d134e9da0dd8480e66aa3414cebe9
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c65426c729b86309e34a+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e8aaeecce4a92a252b53571864061c205302aa8e67996b1c8bafe39da2ce03d
+size 5581824
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c77c617e0f686c6e9c00+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c77c617e0f686c6e9c00+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c77c617e0f686c6e9c00+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c77c617e0f686c6e9c00+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c77c617e0f686c6e9c00+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c77c617e0f686c6e9c00+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c77c617e0f686c6e9c00+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..f2b2f00a3960a83eded4796a18b378016f947238
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c77c617e0f686c6e9c00+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:202b8a31c7744a58f5aa5210ea55aef9c4027a89e5a47aead418940fc1ff917e
+size 363555
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_c77c617e0f686c6e9c00+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c77c617e0f686c6e9c00+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..d92c676a172136fcc662b803a6daf0957d63b86f
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_c77c617e0f686c6e9c00+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24bad8d14752ba0eed5b4ebfeaa8df2bc9a052d28604aac7d85b6421a441d816
+size 3093504
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_cc1727b893df6b3b25c5+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_cc1727b893df6b3b25c5+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_cc1727b893df6b3b25c5+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_cc1727b893df6b3b25c5+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_cc1727b893df6b3b25c5+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_cc1727b893df6b3b25c5+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_cc1727b893df6b3b25c5+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..188adbd60ba8d2e0ad0e0141586d420ee40f27eb
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_cc1727b893df6b3b25c5+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b173ee01163aeb8262e0e98424416772a101da5d6338be6789d9142695021996
+size 165606
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_cc1727b893df6b3b25c5+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_cc1727b893df6b3b25c5+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..965e6d6f9a040e74d3ffa23528cc8f643db8e7a6
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_cc1727b893df6b3b25c5+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c126c34bfd968d0172a8d2471de66c85210c36729f4da351b1f89a1743c0d65c
+size 1455104
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_ce4004e47d7f9259e48d+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ce4004e47d7f9259e48d+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ce4004e47d7f9259e48d+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_ce4004e47d7f9259e48d+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ce4004e47d7f9259e48d+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_ce4004e47d7f9259e48d+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ce4004e47d7f9259e48d+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..de7c6f5382f53550ef33ad81e9595d37a12cdc2d
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ce4004e47d7f9259e48d+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:307cca2614707771ceff6abcef6a2eff2775bd90144f5e7df0cadeada0a9ea86
+size 266465
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_ce4004e47d7f9259e48d+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ce4004e47d7f9259e48d+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..492cf24441b6eb135e9fad9ee60ad84ef881cfd8
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ce4004e47d7f9259e48d+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b827a7ff8d5c2d20692f13db4ab3bb0f0bafbc35adc052c3f436ed06d6a06608
+size 6298624
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_cee1eefa9c3af642bf9b+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_cee1eefa9c3af642bf9b+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_cee1eefa9c3af642bf9b+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_cee1eefa9c3af642bf9b+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_cee1eefa9c3af642bf9b+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_cee1eefa9c3af642bf9b+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_cee1eefa9c3af642bf9b+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..1ceaf79a5c1fde9a49da6645ea5f049e8ec6f322
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_cee1eefa9c3af642bf9b+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e51f6fa40b53ac708cbc1982d2bbdeacc245015c73dfd74ae6b557d1950deb
+size 448637
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_cee1eefa9c3af642bf9b+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_cee1eefa9c3af642bf9b+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..01870ab89b4b4fe3d1bce7a28bb8bcec4e54c6ee
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_cee1eefa9c3af642bf9b+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0142f8fc008fa0c03486b245f4bb55b6c54ce82367a5fbc25e93d3c90a6e5393
+size 30055424
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_d19b002f79730c2890a1+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d19b002f79730c2890a1+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d19b002f79730c2890a1+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_d19b002f79730c2890a1+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d19b002f79730c2890a1+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_d19b002f79730c2890a1+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d19b002f79730c2890a1+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..a677afcfe2298c691b1544fd05e66ec617090abb
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d19b002f79730c2890a1+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb7ab9f641192253bd227ff25c6cf388393301d82de0fb354c1e85e45508e7b
+size 165606
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_d19b002f79730c2890a1+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d19b002f79730c2890a1+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..67443dc765ffec235e33405ec6b98e08d5abfd51
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d19b002f79730c2890a1+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53699df840d3dfcc952aa0a7593269e1318fa9ce282af9662ef46728825b7a51
+size 1362944
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_d656e4c29e525a64d500+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d656e4c29e525a64d500+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d656e4c29e525a64d500+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_d656e4c29e525a64d500+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d656e4c29e525a64d500+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_d656e4c29e525a64d500+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d656e4c29e525a64d500+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..6fe8811a83ccf53075103a07a3714b0f6f0eaf2e
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d656e4c29e525a64d500+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ffdb15fbedfcbf41ac433f6e681931cf05fe3e1c2bfda0c4bc27be2090be1a8
+size 254241
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_d656e4c29e525a64d500+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d656e4c29e525a64d500+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..152e60c42604f0fa2b0f74bb418b1aa39368bd7d
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d656e4c29e525a64d500+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca734200f5d8f08cecd6b10a74f8c93454e4075d9d543a3c0f7176b2b1b27ad
+size 3195904
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_d83898ae6200d4ae727b+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d83898ae6200d4ae727b+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d83898ae6200d4ae727b+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_d83898ae6200d4ae727b+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d83898ae6200d4ae727b+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_d83898ae6200d4ae727b+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d83898ae6200d4ae727b+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..a8504029e4793024bfefb34ebc862978b65de4a6
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d83898ae6200d4ae727b+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f392ecf02ff2ed5b958e0b6b0d06f6e7cec430cf1e392fc4cd5724123b592460
+size 444642
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_d83898ae6200d4ae727b+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d83898ae6200d4ae727b+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b77a5c3015f8630aad80c1a7006bc1fa6051f0ae
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_d83898ae6200d4ae727b+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df04546c7f624324fb534e9fe9edf5c97656e540f9be463d2c25cd48de02e89b
+size 14982144
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_dfb4e18dbbfd0e05a6e6+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_dfb4e18dbbfd0e05a6e6+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_dfb4e18dbbfd0e05a6e6+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_dfb4e18dbbfd0e05a6e6+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_dfb4e18dbbfd0e05a6e6+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_dfb4e18dbbfd0e05a6e6+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_dfb4e18dbbfd0e05a6e6+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..fceb8bef1304111ae71427a01a0d2cff4ec1f6d9
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_dfb4e18dbbfd0e05a6e6+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:901cf94c89a5d9b9b7a8a58a3c06ee675cbd2604d0d6282a31b605ca6f85a0c2
+size 290456
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_dfb4e18dbbfd0e05a6e6+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_dfb4e18dbbfd0e05a6e6+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..fb3d398ed7951ff6ea0c8d6ac023b0e0543134ea
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_dfb4e18dbbfd0e05a6e6+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01b8f1975a20108808789b08288a3c96db30c896003b304f6bffa29a37b7699
+size 3113984
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_e049342bf50290d2724f+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_e049342bf50290d2724f+39f12043/model.neff
index 90caeb56c9670639b605afcd4ed5b8b8f2c0af33..819bc807c78600f970e711878bb64d365b6934b6 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_e049342bf50290d2724f+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_e049342bf50290d2724f+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3798b332c7672e432e32c416e2cc1d3db10c7c0bedd17d13f8bed863d240ccb4
+oid sha256:5b47ea618b283ee90d6320e32d49c1d3ddeb1dbf352f3f56db4547d43eca6bf8
 size 2294784
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_e74e42052287a9d269b6+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_e74e42052287a9d269b6+39f12043/model.neff
index 2d408e8159bb06299328ac922968dd04475c0069..9465adc087c167c9c354e55137a85ea21722a67a 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_e74e42052287a9d269b6+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_e74e42052287a9d269b6+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a232beca5e8993bc5dc0f515ad6abe1a88bb37436b02468da823c668312bac
+oid sha256:be830f965339d49c908b30e9b8eda573191780eca6f47718dd88fcb19db71087
 size 3574784
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_e75ae599b9ad78a80b9b+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_e75ae599b9ad78a80b9b+39f12043/model.neff
index fdc43e1672611a55b36c75836df4b31c9ca37760..f4ed73657c6ec3e1a7b0839b4acf66d17978f78d 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_e75ae599b9ad78a80b9b+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_e75ae599b9ad78a80b9b+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40ebba538d27c365616ae741348331027400f15dfa2abebcde4c3d7c6b5e2f69
+oid sha256:878bb6a1eb76d7d5a86ada8272b002b8f5da9d81c86ae4417749e5178c2b5e51
 size 30915584
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_e9508c7d41b1f29d36fc+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_e9508c7d41b1f29d36fc+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_e9508c7d41b1f29d36fc+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_e9508c7d41b1f29d36fc+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_e9508c7d41b1f29d36fc+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_e9508c7d41b1f29d36fc+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_e9508c7d41b1f29d36fc+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..91cd3c19ed000b93781da00af8d9a1b7a9d5b276
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_e9508c7d41b1f29d36fc+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f11b8aa96663b965a0a3379ec05eb91c4a17017bed9a703cdaba421496569e0
+size 128217
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_e9508c7d41b1f29d36fc+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_e9508c7d41b1f29d36fc+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..c0bbc9927904314ac8ba4348aa782af64056014c
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_e9508c7d41b1f29d36fc+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e100368b2bd5e173cce37a77f43e37b10b522f73456f94c30dd5ce12e7f63cb
+size 2038784
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_ec7ce1cb59fb29fdc73b+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ec7ce1cb59fb29fdc73b+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ec7ce1cb59fb29fdc73b+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_ec7ce1cb59fb29fdc73b+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ec7ce1cb59fb29fdc73b+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_ec7ce1cb59fb29fdc73b+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ec7ce1cb59fb29fdc73b+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..6eedcc9882e5f553deeb6cc857ced29e6c8b6fa1
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ec7ce1cb59fb29fdc73b+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad029fc036db228e823572c9f3eeaef535fbeaacadee653750fea0de5c3e9c7
+size 266465
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_ec7ce1cb59fb29fdc73b+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ec7ce1cb59fb29fdc73b+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..769e0023265acf2279d662152d75ec0b08f3c8f5
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ec7ce1cb59fb29fdc73b+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d00b1bd282d85e1c1a54d14a628009a096087c7aa48048a9c97a2817a855c56
+size 2868224
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_ede85a6c2ef194dd17ba+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ede85a6c2ef194dd17ba+39f12043/model.neff
index 5e8134706bcbfc7321d3b540cd304cc837fc4f05..786bae693aed75b29d3cce9f74e673c5d458f881 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_ede85a6c2ef194dd17ba+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ede85a6c2ef194dd17ba+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb4dde2f1766bdbaa954c6f5746eb4892069954e06a6c4a2bf88fd805b689bda
+oid sha256:31d33f71c7607890590f89151a5999fc20f6dd07542c69451bd34f0727e48bd6
 size 2601984
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_efddfbc496e02d36ff87+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_efddfbc496e02d36ff87+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_efddfbc496e02d36ff87+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_efddfbc496e02d36ff87+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_efddfbc496e02d36ff87+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_efddfbc496e02d36ff87+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_efddfbc496e02d36ff87+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..38c41a8cf95d0ca0fbdf555ce98cc013449fc042
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_efddfbc496e02d36ff87+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcb5b46b1f7600880fa23574fde3e521346cae8b0ff273c819a7315c6b65c712
+size 126426
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_efddfbc496e02d36ff87+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_efddfbc496e02d36ff87+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..8862de890822e6271c0a8d539684b68843c2cb1f
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_efddfbc496e02d36ff87+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44c1f145b7de405d3d22ab19b6d9f5054e522ba405728112a4b6416aaab0851
+size 1557504
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_efe3043beb76da374beb+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_efe3043beb76da374beb+39f12043/model.neff
index 08867e25c21eb218f01909cd6ec4b7b287a44f55..621f24a473978ee1dda3ca6116cadba7f52d05f1 100644
--- a/neuronxcc-2.15.128.0+56dc5a86/MODULE_efe3043beb76da374beb+39f12043/model.neff
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_efe3043beb76da374beb+39f12043/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb71fcc4299298e8e50de0b0bb7c38410060e0792e6bb42f5206ad33c0b5ed1d
+oid sha256:94c576863281ff40b08d09c9ccc25fc584d43e9e9c311ff6881ffb70ea17e889
 size 2274304
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f10dd3b89a824c879736+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f10dd3b89a824c879736+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f10dd3b89a824c879736+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f10dd3b89a824c879736+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f10dd3b89a824c879736+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f10dd3b89a824c879736+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f10dd3b89a824c879736+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..8e7e548f5e0e375ed3c6fbb8b209e5a39d2943f8
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f10dd3b89a824c879736+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf2649ac957aa8302c01977d4a445ca5e95a70c45610d311ce2ad487abcb4b3
+size 224577
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f10dd3b89a824c879736+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f10dd3b89a824c879736+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..c086d0fdf01a562e42f7a8255bc78d0d63942147
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f10dd3b89a824c879736+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46b23e443765c70943e8de0b6246e1e1deb6620a1609a2650cf93c7b845d79f4
+size 3912704
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f34e4ed3c28e63eda19b+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f34e4ed3c28e63eda19b+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f34e4ed3c28e63eda19b+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f34e4ed3c28e63eda19b+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f34e4ed3c28e63eda19b+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f34e4ed3c28e63eda19b+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f34e4ed3c28e63eda19b+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..6a97357f288ecfb0bac25e7d9065c5284d0c52d6
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f34e4ed3c28e63eda19b+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ed83fdb93019c26d5f9f6e132ee0c1f539eae61de59d94754d3dc16f728c97
+size 448637
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f34e4ed3c28e63eda19b+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f34e4ed3c28e63eda19b+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..6b8ebc506959f606911d879255da7879ddf13cf6
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f34e4ed3c28e63eda19b+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dddd8b141bd793ca1ae62a1e7abb3a88b4f94b4f75ad57c3d82f69587a0c7a29
+size 30055424
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f4d26174266564b9c206+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f4d26174266564b9c206+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f4d26174266564b9c206+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f4d26174266564b9c206+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f4d26174266564b9c206+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f4d26174266564b9c206+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f4d26174266564b9c206+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..1828639ae4d2c7e8599faf29a086d52506e3a321
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f4d26174266564b9c206+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ecd59e27b4986fce3e5c13a440c1cd58243d80831a0b6396aae8f097de8389
+size 254241
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f4d26174266564b9c206+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f4d26174266564b9c206+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..52b4086a3fb6d31a8b7b98c826ce71d4d4036ea7
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f4d26174266564b9c206+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca209b05bf033458b5e527ea3f2da87b2e31bc432931e9784856fc3182535ad
+size 18965504
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f93de83e0c3ea0bb06cc+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f93de83e0c3ea0bb06cc+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f93de83e0c3ea0bb06cc+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f93de83e0c3ea0bb06cc+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f93de83e0c3ea0bb06cc+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f93de83e0c3ea0bb06cc+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f93de83e0c3ea0bb06cc+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..c5b0b0c412de57974b1336f7a3328f0f8db97584
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f93de83e0c3ea0bb06cc+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15782a720079106495d156ca3eb1430bbc0ff6ae62e0d1dffbf30599a4d2be8a
+size 556389
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_f93de83e0c3ea0bb06cc+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f93de83e0c3ea0bb06cc+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..f3c09d761c5df2cfdac84b6bbc4d847772ba011a
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_f93de83e0c3ea0bb06cc+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc0c20281a50d5a4325100c504fa94073bea7c6d6653b98d8ee2d3421c07654d
+size 5100544
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_ff1977202245df118119+39f12043/compile_flags.json b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ff1977202245df118119+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ff1977202245df118119+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_ff1977202245df118119+39f12043/model.done b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ff1977202245df118119+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_ff1977202245df118119+39f12043/model.hlo_module.pb b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ff1977202245df118119+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..4a36808444a0f1900833c659b2736bccdc32fa34
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ff1977202245df118119+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c07693bc966c06e9e4385f06aff1f1275f3cde24c4ebfd28218821198ea55f0a
+size 318032
diff --git a/neuronxcc-2.15.128.0+56dc5a86/MODULE_ff1977202245df118119+39f12043/model.neff b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ff1977202245df118119+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..e00f20c2b2a702bb3fe10b625fb92dde7ae2e788
--- /dev/null
+++ b/neuronxcc-2.15.128.0+56dc5a86/MODULE_ff1977202245df118119+39f12043/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d64883170aad7176c481b6735f0c6a0d07ffa039e9a475becac06bdc40b7d2
+size 6401024