Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
474
jburtoft commited on
Commit
69a2545
·
verified ·
1 Parent(s): 7f86cad

Synchronizing local compiler cache.

Browse files
Files changed (28) hide show
  1. .gitattributes +6 -0
  2. neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3.1-8B-Instruct/441d7cd85e3f495e5cd5.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3.1-8B-Instruct/92d116087e75663201c6.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3.1-8B-Instruct/fda71f4ed842b3b05b6d.json +1 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_0b17d247a29c381a6ede+613edded/compile_flags.json +1 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_0b17d247a29c381a6ede+613edded/model.done +0 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_0b17d247a29c381a6ede+613edded/model.hlo_module.pb +3 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_0b17d247a29c381a6ede+613edded/model.neff +3 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_255d9903625be118be58+613edded/compile_flags.json +1 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_255d9903625be118be58+613edded/model.done +0 -0
  11. neuronxcc-2.16.372.0+4a9b2326/MODULE_255d9903625be118be58+613edded/model.hlo_module.pb +3 -0
  12. neuronxcc-2.16.372.0+4a9b2326/MODULE_255d9903625be118be58+613edded/model.neff +3 -0
  13. neuronxcc-2.16.372.0+4a9b2326/MODULE_284cb3ffef586348809d+613edded/compile_flags.json +1 -0
  14. neuronxcc-2.16.372.0+4a9b2326/MODULE_284cb3ffef586348809d+613edded/model.done +0 -0
  15. neuronxcc-2.16.372.0+4a9b2326/MODULE_284cb3ffef586348809d+613edded/model.hlo_module.pb +3 -0
  16. neuronxcc-2.16.372.0+4a9b2326/MODULE_284cb3ffef586348809d+613edded/model.neff +3 -0
  17. neuronxcc-2.16.372.0+4a9b2326/MODULE_629b0269219133666d97+613edded/compile_flags.json +1 -0
  18. neuronxcc-2.16.372.0+4a9b2326/MODULE_629b0269219133666d97+613edded/model.done +0 -0
  19. neuronxcc-2.16.372.0+4a9b2326/MODULE_629b0269219133666d97+613edded/model.hlo_module.pb +3 -0
  20. neuronxcc-2.16.372.0+4a9b2326/MODULE_629b0269219133666d97+613edded/model.neff +3 -0
  21. neuronxcc-2.16.372.0+4a9b2326/MODULE_841dfee8bfd94697be95+613edded/compile_flags.json +1 -0
  22. neuronxcc-2.16.372.0+4a9b2326/MODULE_841dfee8bfd94697be95+613edded/model.done +0 -0
  23. neuronxcc-2.16.372.0+4a9b2326/MODULE_841dfee8bfd94697be95+613edded/model.hlo_module.pb +3 -0
  24. neuronxcc-2.16.372.0+4a9b2326/MODULE_841dfee8bfd94697be95+613edded/model.neff +3 -0
  25. neuronxcc-2.16.372.0+4a9b2326/MODULE_cf84f1c0bff507b086e0+613edded/compile_flags.json +1 -0
  26. neuronxcc-2.16.372.0+4a9b2326/MODULE_cf84f1c0bff507b086e0+613edded/model.done +0 -0
  27. neuronxcc-2.16.372.0+4a9b2326/MODULE_cf84f1c0bff507b086e0+613edded/model.hlo_module.pb +3 -0
  28. neuronxcc-2.16.372.0+4a9b2326/MODULE_cf84f1c0bff507b086e0+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -8288,3 +8288,9 @@ neuronxcc-2.17.194.0+d312836f/MODULE_fb9e4f974acc74d766dc+165e9558/model.neff fi
8288
  neuronxcc-2.17.194.0+d312836f/MODULE_fb9e4f974acc74d766dc+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
8289
  neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
8290
  neuronxcc-2.17.194.0+d312836f/MODULE_fffbb7a74f126b7cac4f+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
8288
  neuronxcc-2.17.194.0+d312836f/MODULE_fb9e4f974acc74d766dc+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
8289
  neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
8290
  neuronxcc-2.17.194.0+d312836f/MODULE_fffbb7a74f126b7cac4f+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
8291
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_0b17d247a29c381a6ede+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
8292
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_255d9903625be118be58+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
8293
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_284cb3ffef586348809d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
8294
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_629b0269219133666d97+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
8295
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_841dfee8bfd94697be95+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
8296
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_cf84f1c0bff507b086e0+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3.1-8B-Instruct/441d7cd85e3f495e5cd5.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "head_dim": 128, "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-Instruct", "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "sequence_length": 10240, "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}
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3.1-8B-Instruct/92d116087e75663201c6.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "head_dim": 128, "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": "0e9e39f249a16976918f6564b8830bc894c89659", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "sequence_length": 10240, "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}
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3.1-8B-Instruct/fda71f4ed842b3b05b6d.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "head_dim": 128, "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-Instruct", "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "sequence_length": 10240, "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}
neuronxcc-2.16.372.0+4a9b2326/MODULE_0b17d247a29c381a6ede+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.16.372.0+4a9b2326/MODULE_0b17d247a29c381a6ede+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_0b17d247a29c381a6ede+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ab40fef67993cd0eacdeef7a7da38cbcb0ff42575126e657fcfaf4057f70758
3
+ size 401133
neuronxcc-2.16.372.0+4a9b2326/MODULE_0b17d247a29c381a6ede+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:008d2f32cbd47a6ce456d21f7f60005dd83d46b6a181d525b02b5a382d68c971
3
+ size 5817344
neuronxcc-2.16.372.0+4a9b2326/MODULE_255d9903625be118be58+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.16.372.0+4a9b2326/MODULE_255d9903625be118be58+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_255d9903625be118be58+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeb2ac215a5d8df6e17cdab8781139072901a13946cc5d98b728d8d16784e4e9
3
+ size 363567
neuronxcc-2.16.372.0+4a9b2326/MODULE_255d9903625be118be58+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6968db7406eec6617e88c073dc13d9afe43ed47fb86048b82bb4e84108621359
3
+ size 5929984
neuronxcc-2.16.372.0+4a9b2326/MODULE_284cb3ffef586348809d+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.16.372.0+4a9b2326/MODULE_284cb3ffef586348809d+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_284cb3ffef586348809d+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ece8ecf12c36aad192bafa8c1b9381c4d3264da6c28f1915e27f4b4d6a1bc05
3
+ size 331676
neuronxcc-2.16.372.0+4a9b2326/MODULE_284cb3ffef586348809d+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c887722970f13b372a7e21c0785e2cbf188c7a6ecdbe3b1a8472bdf88f39cfcd
3
+ size 2714624
neuronxcc-2.16.372.0+4a9b2326/MODULE_629b0269219133666d97+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.16.372.0+4a9b2326/MODULE_629b0269219133666d97+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_629b0269219133666d97+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4935a78fbbc9a6304c50ffc18b6bf048e37360ad3b7ceb272abc416b83aafe9
3
+ size 446729
neuronxcc-2.16.372.0+4a9b2326/MODULE_629b0269219133666d97+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a04b2edb7b633f78e91762e80814aedbe4a94575bf9f06acc34705cd5511124
3
+ size 5848064
neuronxcc-2.16.372.0+4a9b2326/MODULE_841dfee8bfd94697be95+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.16.372.0+4a9b2326/MODULE_841dfee8bfd94697be95+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_841dfee8bfd94697be95+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d79e8997badc20fb5aca9b1fd1bd2c7bdc0843a43f195754d3a35b554ccdb754
3
+ size 363567
neuronxcc-2.16.372.0+4a9b2326/MODULE_841dfee8bfd94697be95+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec5835a32bc6f86e8c2623877086d08a0414e4daf57d5855f059452cffb0915c
3
+ size 10753024
neuronxcc-2.16.372.0+4a9b2326/MODULE_cf84f1c0bff507b086e0+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.16.372.0+4a9b2326/MODULE_cf84f1c0bff507b086e0+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_cf84f1c0bff507b086e0+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d330fe44dc352a37b3c3fcb1443421db3e32b71e391f4630db33564b4fa7ad1e
3
+ size 446729
neuronxcc-2.16.372.0+4a9b2326/MODULE_cf84f1c0bff507b086e0+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad7740b0f2e6066be3b33ba6c7acb2696b4df482746dee77dca3b5c8876b3fb
3
+ size 5848064