init

README.md

@@ -1,3 +0,0 @@
----
-license: apache-2.0
----

config.json

@@ -0,0 +1 @@
+{"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mixtral", "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 32, "num_key_value_heads": 8, "num_local_experts": 6, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.02, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.36.0.dev0", "use_cache": true, "vocab_size": 32000}

model-00001-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80273a75ca68cbbc9370045215756c13c11e69ec71c010d3d673a2188c07d2c6
+size 3835811024

model-00002-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d58a25788485a1d3f3217bad0d1c851a35247704e71ea030b8c94f4097429319
+size 3808564816

model-00003-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c473bb3db849c875fb8d428e12998b85a970469edcef053c8da786d05f4f76c
+size 3691124176

model-00004-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ecf976e8d78008f67776afa92b48b529f9c5ffff1eb2661b3eff57d346808ff
+size 3607171744

model-00005-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc9da6deb4fdded2f88644ac4c192983da58c386d8a7a1395a24810ec0e93a4
+size 3808564816

model-00006-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b4e13aa4bf16a28a9745448f1513bec990813746eb6b7d3bf4f018e9bbf3e6
+size 3926005464

model-00007-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006d03ee9563ba4e685db875cf8c9147062ce917cd5a77a51973d324e368a6e7
+size 3489731136

model-00008-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50dbf23720b745f8dad74f34d89623c2b7da3831e1cb1180f9e6d1f24a67d217
+size 3926005504

model-00009-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b56f438e24eb43ae68086a4b0662b5c17caa4f105c37aeb9c79971e6c95f7a8
+size 3926005504

model-00010-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c5b0a30dd538b64f77a04c6980d1794306055b1cd65c6fd9a0edc12f69581b
+size 3489731136

model-00011-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8901a7df79b0549adaadcc51e38ea8173a213bd425452f05d0cd9fa835086293
+size 3808564864

model-00012-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe5447d1ad8512b3ae63d0bd258f59df0013986fca49e35c55a630771da4bd41
+size 3691124216

model-00013-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dad811a5fb03ad5eed4e2e540a124afb7b1301f6c2ec436dba3d28dbf47282c5
+size 3926005512

model-00014-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:795adad9d242e9c7b214e5d5d9e21d5fb3a074a126e0fb075d3f508f2a7abc47
+size 3489731136

model-00015-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6542893d0c5e125bd794be4b21c27fd647817dc74d7f77e3695df012a2c5f07e
+size 3926005504

model-00016-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1cd51b5ff00e63d417c0216b9fe0f0f810b72b17950dced9524c1de7289f756
+size 3926005512

model-00017-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef9c90c69c0a4a018590a365ff7246652359ac3e74a43e95a8f99a20f994582d
+size 3489731136

model-00018-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6514aed280e2ec066975daab3381fdcbd7961f4d12897a9f81fb05a14983df0f
+size 3926005504

model-00019-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af04656e7d2b0307e4cae0bc299840f6a1fce5844a732f684d31fa4326e3fdac
+size 3164696904

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 93405585408}, "weight_map": {"model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00019.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00015-of-00019.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00015-of-00019.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00019.safetensors", "model.layers.15.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00010-of-00019.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00019.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00019.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00019.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00012-of-00019.safetensors", "model.layers.19.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00019.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00012-of-00019.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00019.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00002-of-00019.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00019.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00019.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00014-of-00019.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00019.safetensors", "model.layers.10.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00007-of-00019.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00019.safetensors", "model.layers.11.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00019.safetensors", "model.layers.12.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00019.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.embed_tokens.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00019.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00019.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00016-of-00019.safetensors", "model.layers.26.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00019.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00016-of-00019.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00019.safetensors", "model.layers.13.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00009-of-00019.safetensors", "model.layers.14.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00009-of-00019.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00019.safetensors", "model.layers.16.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00011-of-00019.safetensors", "model.layers.17.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00011-of-00019.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00019.safetensors", "model.layers.20.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00019.safetensors", "model.layers.21.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00019.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00019.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00019.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00019.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00019.safetensors", "model.layers.9.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00019.safetensors", "model.layers.27.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00017-of-00019.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "lm_head.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00019.safetensors", "model.layers.30.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.31.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00019.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00019-of-00019.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.norm.weight": "model-00019-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00019.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00019.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00003-of-00019.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00019.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00019.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00019.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00019.safetensors", "model.layers.28.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00018-of-00019.safetensors", "model.layers.29.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00018-of-00019.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00019.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}"
+}