Upload folder using huggingface_hub

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "BioMistral/BioMistral-7B",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,24 @@
+base_model: BioMistral/BioMistral-7B
+gate_mode: random # one of "hidden", "cheap_embed", or "random"
+dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
+## (optional)
+# experts_per_token: 2
+experts:
+  - source_model: Treza12/Biomistral-Class0-Full
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Screening"
+  - source_model: Treza12/Biomistral-Class1-Full
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Diagnosis"
+  - source_model: Treza12/Biomistral-Class2-Full
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Staging"
+  - source_model: Treza12/Biomistral-Class3-Full
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Treatment Selection"
+  - source_model: Treza12/Biomistral-Class4-Full
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Prognosis" 
+  - source_model: Treza12/Biomistral-Class5-Full
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Follow-up" 

model-00001-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3781529025991ef1bd1406fcc353bdd90db0ce005ce781246eabbd979181a056
+size 991971528

model-00002-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a09f1a75eea8ce59d5754f15502be3b65da519096d1eaff1f3b2fa7320c0881
+size 964708960

model-00003-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e3259634c9e38770c27d0319e20ee1c5b3eaab8c0d73fe4b54245afb64ba84
+size 964708960

model-00004-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e42785d9c512686b7741735ae9fb8d3261568288cfc6e169563047895062f70
+size 964708960

model-00005-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eed39c23744e146079b9545dd803ecfc3356219a7c9e8473e0743ac7e346fb8
+size 989866488

model-00006-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69ad323f92c251811cbd3e166e4d7a6067b8b54f53ad9c460ea5abb1a4f37676
+size 973089048

model-00007-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70e17d13c35fb066805a73d4bed73b36887844841a176698473256329e8c140
+size 964708960

model-00008-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e15bcfd6bc4ed6d0ff2e3f3c982dc9614827cf819c966e967e106dc274422f1f
+size 964708960

model-00009-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89def0659d90cb05eb0528bbf9360d16a447ea67d1c8650cbea43ac116678999
+size 964708960

model-00010-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a5d4c63a3ddc66ca4ccdaa96b9d4c03d8ace24f6283a98864fed59555765aa8
+size 964708960

model-00011-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c126a1d92209b23b72f3311c3715ffc384eef5919567ea1b13d9f6f8f9c61f02
+size 964708960

model-00012-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a945fae367cc6ec84dd7b83eda9d1efb02e3a4a855546b9d0d16b208628334b
+size 998254872

model-00013-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60a62003995620169af414be28a4569a88dac4213567471f0386f9b2214e6f7
+size 964700680

model-00014-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f788bad8013e8b2ddc8f49957148b5355529fb1fd9a5bdfe6183624d743b7393
+size 964708984

model-00015-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0831d7f27d340d9aed22c4beed135da679d3328037ade9ffda1b7f8c5f0136
+size 964708984

model-00016-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:086588be69c3d3f2c63897b5a5b9f9ff14ecdbaa30764d3c8d8d82573270fff7
+size 964708984

model-00017-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb447b0bea91ecbc8bb694c2cb77faebe8a7581294b9e52db1af79bbd2376f2
+size 964708984

model-00018-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab780036120ae665e48322b419b0f8349c342baf519e2a3c4cbf6a22d2121349
+size 964708984

model-00019-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9704cc0ac983b43585ebe232ee0086f693001b51c175ece7a9a1c1f5b61a7f48
+size 998246592

model-00020-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d2b531e185b870fd036f2e59ab0e9559d611b5f4a4dc80c7b7ea01695ad473
+size 964708984

model-00021-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e70eef55be824f152a3a03a13091dc458654bced9d8d723f71007687852cc199
+size 964708984

model-00022-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833f494ae3fe1964dfbce68d0a683789bdd1a78476863b6c7ddbce415ba3db30
+size 964708984

model-00023-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc53726a023b28f941271dfbdb603d3387debb0d365ec66deb524b07c42d17f4
+size 964708984

model-00024-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd7dbaa0e9b3f29e4f2d4334d7f416c8da6c9e5472589c007b0c006ccd8f6f44
+size 964708984

model-00025-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3175ae0a5cbbbcfcd49c7d0cab2324f286f17dd8873173090c652b163f1d7d7
+size 989866504

model-00026-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b3987c3262d4c975baf830b1230be26a9d586c171c38f660a2a60bf36234ce
+size 973089072

model-00027-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c67f91c03f642eb22e1481d50c7b09708f89ab290453fae91ffc7bd32d0a3ec
+size 964708984

model-00028-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70378ce0fe2989ff3b2b6cee8a6cbd8c452d8fffd3aad8d9be350728530df511
+size 964708984

model-00029-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b39e9d077105ce924b54bd50d1e8509b21f906e2c02b0c3933f0fd54240c7a
+size 964708984

model-00030-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c380d480053529e617efa02aa27885fff69e117de9296494ef2ee106c08557c
+size 964708984

model-00031-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c10428832d936042f2778fe538a1b6e4f55abc381c4ce0597570de81f28d4e8
+size 964708984

model-00032-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:690a6646c30c04e82627fea71c2f05f8abb432e5850ff5265a80010b85f7e1f7
+size 998254896

model-00033-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac759591a7778e396f69924257373a8893e82f76301f3281518cc7c79df3c4db
+size 964700680

model-00034-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b200a0462690242c34e9fb88774902e27dc491fcac956b72cfb7499b787df6
+size 964708984

model-00035-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b08145103b477dfe1b6e40479e62106520eed1fdb199db28370ff5c724a29d
+size 964708984

model-00036-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9cd66436ccadeba60c63c241aa29fb2c43044e3a2ddd6de1ff9a354dc599940
+size 964708984

model-00037-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ac55a2c5bcf5100b1d40661a2b292dd69a3c4bd43e1f7f1f2daeae563038b9a
+size 964708984

model-00038-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adf04cbe24430504604daef6e4c78a02e994291e9e2294d6b179c5201a630dce
+size 880814104

model-00039-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dffd167ddd950c229be6cf01480b6dcc6f272d07a3bb534435bcfcb27acac3a8
+size 263720760

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 37033615360}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00039.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00039.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00039.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00039.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00039.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00039.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00039.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00039.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00039.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00039.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00039.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00039.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00039.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00039.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00039.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00039.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00039.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00039.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00039.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00039.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00039.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00039.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00039.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00039.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00039.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00039.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00039.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00039.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00039.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00039.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00039.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00039.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00039.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00039.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00039.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00039.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00039.safetensors", "model.layers.6.input_layernorm.weight": "model-00008-of-00039.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00008-of-00039.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00039.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00039.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00039.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00039.safetensors", "model.layers.7.input_layernorm.weight": "model-00009-of-00039.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00009-of-00039.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00009-of-00039.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00009-of-00039.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00009-of-00039.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00039.safetensors", "model.layers.8.input_layernorm.weight": "model-00010-of-00039.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00039.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00039.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00039.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00039.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00039.safetensors", "model.layers.9.input_layernorm.weight": "model-00011-of-00039.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00039.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00011-of-00039.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00011-of-00039.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00011-of-00039.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00039.safetensors", "model.layers.10.input_layernorm.weight": "model-00012-of-00039.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00013-of-00039.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00013-of-00039.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00013-of-00039.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00013-of-00039.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00039.safetensors", "model.layers.11.input_layernorm.weight": "model-00014-of-00039.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00014-of-00039.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00014-of-00039.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00014-of-00039.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00014-of-00039.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00039.safetensors", "model.layers.12.input_layernorm.weight": "model-00015-of-00039.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00015-of-00039.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00015-of-00039.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00015-of-00039.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00015-of-00039.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00039.safetensors", "model.layers.13.input_layernorm.weight": "model-00016-of-00039.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00016-of-00039.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00016-of-00039.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00016-of-00039.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00016-of-00039.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00016-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00039.safetensors", "model.layers.14.input_layernorm.weight": "model-00017-of-00039.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00017-of-00039.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00017-of-00039.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00017-of-00039.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00017-of-00039.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00017-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00039.safetensors", "model.layers.15.input_layernorm.weight": "model-00018-of-00039.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00018-of-00039.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00018-of-00039.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00018-of-00039.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00018-of-00039.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00018-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00020-of-00039.safetensors", "model.layers.16.input_layernorm.weight": "model-00020-of-00039.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00020-of-00039.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00020-of-00039.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00020-of-00039.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00020-of-00039.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00021-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00021-of-00039.safetensors", "model.layers.17.input_layernorm.weight": "model-00021-of-00039.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00021-of-00039.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00021-of-00039.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00021-of-00039.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00021-of-00039.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00022-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00022-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00022-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00022-of-00039.safetensors", "model.layers.18.input_layernorm.weight": "model-00022-of-00039.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00022-of-00039.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00022-of-00039.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00022-of-00039.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00022-of-00039.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00023-of-00039.safetensors", "model.layers.19.input_layernorm.weight": "model-00023-of-00039.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00023-of-00039.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00023-of-00039.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00023-of-00039.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00023-of-00039.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00023-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00023-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00023-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00024-of-00039.safetensors", "model.layers.20.input_layernorm.weight": "model-00024-of-00039.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00024-of-00039.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00024-of-00039.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00024-of-00039.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00024-of-00039.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00024-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00025-of-00039.safetensors", "model.layers.21.input_layernorm.weight": "model-00025-of-00039.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00025-of-00039.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00025-of-00039.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00025-of-00039.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00026-of-00039.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00027-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00027-of-00039.safetensors", "model.layers.22.input_layernorm.weight": "model-00027-of-00039.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00027-of-00039.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00027-of-00039.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00027-of-00039.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00027-of-00039.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00028-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00028-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00028-of-00039.safetensors", "model.layers.23.input_layernorm.weight": "model-00028-of-00039.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00028-of-00039.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00028-of-00039.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00028-of-00039.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00028-of-00039.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00029-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00029-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00029-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00029-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00029-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00029-of-00039.safetensors", "model.layers.24.input_layernorm.weight": "model-00029-of-00039.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00029-of-00039.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00029-of-00039.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00029-of-00039.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00029-of-00039.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00030-of-00039.safetensors", "model.layers.25.input_layernorm.weight": "model-00030-of-00039.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00030-of-00039.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00030-of-00039.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00030-of-00039.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00030-of-00039.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00030-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00030-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00030-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00031-of-00039.safetensors", "model.layers.26.input_layernorm.weight": "model-00031-of-00039.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00031-of-00039.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00031-of-00039.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00031-of-00039.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00031-of-00039.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00031-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00032-of-00039.safetensors", "model.layers.27.input_layernorm.weight": "model-00032-of-00039.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00033-of-00039.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00033-of-00039.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00033-of-00039.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00033-of-00039.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00034-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00034-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00034-of-00039.safetensors", "model.layers.28.input_layernorm.weight": "model-00034-of-00039.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00034-of-00039.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00034-of-00039.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00034-of-00039.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00034-of-00039.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00035-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00035-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00035-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00035-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00035-of-00039.safetensors", "model.layers.29.input_layernorm.weight": "model-00035-of-00039.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00035-of-00039.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00035-of-00039.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00035-of-00039.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00035-of-00039.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00036-of-00039.safetensors", "model.layers.30.input_layernorm.weight": "model-00036-of-00039.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00036-of-00039.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00036-of-00039.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00036-of-00039.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00036-of-00039.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00036-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00036-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00036-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00036-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00036-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00036-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00037-of-00039.safetensors", "model.layers.31.input_layernorm.weight": "model-00037-of-00039.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00037-of-00039.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00037-of-00039.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00037-of-00039.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00037-of-00039.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00037-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00037-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00037-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00038-of-00039.safetensors", "model.norm.weight": "model-00038-of-00039.safetensors", "lm_head.weight": "model-00039-of-00039.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "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 %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}