Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2",
+  "architectures": [
+    "Qwen2MoeForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "mlp_only_layers": [],
+  "model_type": "qwen2_moe",
+  "moe_intermediate_size": 18944,
+  "norm_topk_prob": true,
+  "num_attention_heads": 28,
+  "num_experts": 4,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 18944,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_moe_config.yml

@@ -0,0 +1,21 @@
+
+base_model: huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2
+architecture: qwen
+gate_mode: hidden
+dtype: bfloat16
+experts:
+  - source_model: huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2
+    positive_prompts: ["chat", "assistant", "chat history", "chat context", "writing", "text writing", "editing", "text editing", "multilingual"]
+  - source_model: Qwen/Qwen2.5-Math-1.5B-Instruct
+    positive_prompts: ["bio", "science", "biology", "natural sciences", "scientist", "math", "mathematician", "problem solving", "calculating", "logics"]
+  - source_model: Qwen/Qwen2.5-Coder-3B-Instruct
+    positive_prompts: ["code", "coding", "coder", "programming", "programmer", "code analysis", "code review", "code fix", "code improvement"]
+  - source_model: RefalMachine/ruadapt_qwen2.5_3B_ext_u48_instruct_v4
+    positive_prompts: ["russian chat", "russian chatting", "russian", "russian language", "russian text writing/editing"]
+shared_experts:
+  - source_model: huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2
+    positive_prompts: # required by Qwen MoE for "hidden" gate mode, otherwise not allowed
+      - "chat assistant"
+    # (optional, but recommended:)
+    residual_scale: 0.1 # downweight output from shared expert to prevent overcooking the model
+

model-00001-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01845180ac3f6a4a8110cedd8c044d449b54237c22b7f878b4b35fa6763a4270
+size 1089994896

model-00002-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72e3134368907253d887ac91b9b11e5e805310402e5b3c1fef960c73cb036dd
+size 986981064

model-00003-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6227af32a64401313e4d7745768f5a9bb6579cb966cb175a2072d6e74d18d67
+size 882402648

model-00004-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d705a56272db1189bb910ae5ee18c1ef654033afbe3acf439c0706030a304dd4
+size 973104472

model-00005-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7498d0064481094e95729f67dc5718998f59804d7fe2c30e63fa0bc6c6d55d1f
+size 973104472

model-00006-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a9d4f1a5838b227d309e3365d4369e6692d8815f2e0ae362c76bf663bba1f7
+size 896271968

model-00007-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52f061f151b17e8b662a2690896dd4972e5d421fe8514b1292b0133efb1ec275
+size 973104480

model-00008-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5cbaa82595301dd5d1a37070a8c244b40ae778a0c0a2f439476d56bb67dc85d
+size 973104472

model-00009-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f3c3c399dea7c05fcd8ac9c3ec70ebaa7066dbc30be81d93c0d2fc04aeafb3
+size 955016784

model-00010-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca5236dbc5d39d1342f653b8d59dfab7cb72aa8ea441a7296ec0e02b852fc37e
+size 973104472

model-00011-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d9521a80824cf7a3601ee5c61773d469db288921655c47041e9f855ca6156c1
+size 986973792

model-00012-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ec5aa208de3e55e8315d775d7fc43e26593c99b625fcbe9295cf3084096169
+size 882402648

model-00013-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:719b2ca8bb0b16088fcdfdf37a44dd5b16ddeab168859a122c52f6b36bac6104
+size 973104472

model-00014-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db3c6a6e97549065855996b3bdcb94e324da8e2589ce9f2be0c367beac22cd1
+size 973104464

model-00015-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa077686944cc0780a760bb87ab9e94f50a3bb9d69c340ed3888f0f04ee6f57
+size 896271984

model-00016-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15be6d42d30b0bcca40293e05533ba9f36b5e8b27d9ccd2eb6f36d229e7dd1a0
+size 973104504

model-00017-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:380bc14a2d18914bdc04103c8096cd303800bff52a6a6624320785ff8b011427
+size 973104488

model-00018-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0eff426f01292a2061a7858c4dfe3b0a694cdf5ddba5c0b93ea417a65d1fd14
+size 955016800

model-00019-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5db3f002ad10efe000236c0f294b9149d089bd449c10526a9c74defadc68e04d
+size 973104496

model-00020-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55ffdc920a8bfcde4d684ef1d2a9d09808d8ca884e32b29915774a9eb2bb8360
+size 986973808

model-00021-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e14ab70a489477cbfac968575bf57c1da5065786addbfdea2f87986320166bae
+size 882402672

model-00022-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d079648038245c989f9e1f41a1cd849cce30b688ccf8d20120f6a02c598282
+size 973104496

model-00023-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8275e26d050b6cb254daca41ff183112780d994c2a6dbecedd9d5890b165c019
+size 973104488

model-00024-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2388e6839404a123c7b391ab92172314f10627d3424f21a3760b3524b3a6f9
+size 896271984

model-00025-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c05ca4eb8356319f4931783d9dd1dc2bf31c1d09b5fc1c5b831e20a60c83e64
+size 973104504

model-00026-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80c96ce35a3ab49b774670ff14cc1ba18e6393b8ad89dc3629b4eca38ff00dc6
+size 973104488

model-00027-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4130ae55e0ebc0e48947a1fbee3b21b7cfc83c5fea14240a361ccd614f21b449
+size 955016800

model-00028-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b4f2b173ad22b08d5eaf648046ebf24d3de86bc64372e2a917caeb0fcd5202
+size 973104496

model-00029-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6089378edc3bb79b0895adf6da7b1473f78b4fc1b2d35209e97462010be64382
+size 986973808

model-00030-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9740be09c08c079b95c6eb37324a65a3858564f81eb8fa733255ae0f1134db41
+size 882402672

model-00031-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809e2456a0a09d354b5a7ed9b7f05f39ec147e8eddf46ef98d724d8b29518c24
+size 973104496

model-00032-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e080e130a9669dfc52ffff54e60663970294c7dad21c1eb0d7bd4e6cf524e7e5
+size 973104488

model-00033-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc489427b1d86b8684107ffbe5fd1db51c3c799342da022b3de8cc34f49473a9
+size 896271984

model-00034-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12244c404cfb7b207428e730d1cd30a198dfce268106f596af032e863ef22f58
+size 973104504

model-00035-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05b82a3ec378a65b5b7c745d4f127620624e658a49786c2c95bfbf6bf79355d
+size 973104488

model-00036-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41af5790b1cafaebfac677e0a9b67e19ca5efb29df38b11385ec78861831d942
+size 955016800

model-00037-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17bd14ad25809abe3d6521cf1b907e47db1dc4256653a86e2591a58a834506aa
+size 973104472

model-00038-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06006972c3be88e8a44fe21cfe2b0472b130780c781a741f8f90f1fe5ba3aae2
+size 1089994880

model-00039-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ffcb546461f507e216509a33014b7e02e213ecee6640267e85c80abf143732a
+size 1009464

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 36525669376}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00039.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00039.safetensors", "model.layers.0.mlp.experts.0.down_proj.weight": "model-00002-of-00039.safetensors", "model.layers.0.mlp.experts.1.down_proj.weight": "model-00002-of-00039.safetensors", "model.layers.0.mlp.experts.2.down_proj.weight": "model-00002-of-00039.safetensors", "model.layers.0.mlp.experts.3.down_proj.weight": "model-00002-of-00039.safetensors", "model.layers.0.mlp.shared_expert.down_proj.weight": "model-00002-of-00039.safetensors", "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00002-of-00039.safetensors", "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00002-of-00039.safetensors", "model.layers.0.mlp.experts.2.gate_proj.weight": "model-00002-of-00039.safetensors", "model.layers.0.mlp.experts.3.gate_proj.weight": "model-00002-of-00039.safetensors", "model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00002-of-00039.safetensors", "model.layers.0.mlp.experts.0.up_proj.weight": "model-00002-of-00039.safetensors", "model.layers.0.mlp.experts.1.up_proj.weight": "model-00002-of-00039.safetensors", "model.layers.0.mlp.experts.2.up_proj.weight": "model-00002-of-00039.safetensors", "model.layers.0.mlp.experts.3.up_proj.weight": "model-00003-of-00039.safetensors", "model.layers.0.mlp.shared_expert.up_proj.weight": "model-00003-of-00039.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00039.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00039.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00039.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00039.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00039.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00039.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00039.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00039.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00039.safetensors", "model.layers.1.mlp.experts.0.down_proj.weight": "model-00003-of-00039.safetensors", "model.layers.1.mlp.experts.1.down_proj.weight": "model-00003-of-00039.safetensors", "model.layers.1.mlp.experts.2.down_proj.weight": "model-00003-of-00039.safetensors", "model.layers.1.mlp.experts.3.down_proj.weight": "model-00003-of-00039.safetensors", "model.layers.1.mlp.shared_expert.down_proj.weight": "model-00003-of-00039.safetensors", "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00003-of-00039.safetensors", "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00003-of-00039.safetensors", "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00003-of-00039.safetensors", "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00003-of-00039.safetensors", "model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00004-of-00039.safetensors", "model.layers.1.mlp.experts.0.up_proj.weight": "model-00004-of-00039.safetensors", "model.layers.1.mlp.experts.1.up_proj.weight": "model-00004-of-00039.safetensors", "model.layers.1.mlp.experts.2.up_proj.weight": "model-00004-of-00039.safetensors", "model.layers.1.mlp.experts.3.up_proj.weight": "model-00004-of-00039.safetensors", "model.layers.1.mlp.shared_expert.up_proj.weight": "model-00004-of-00039.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00039.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00004-of-00039.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00039.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00039.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00004-of-00039.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00039.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00004-of-00039.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00039.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00039.safetensors", "model.layers.2.mlp.experts.0.down_proj.weight": "model-00004-of-00039.safetensors", "model.layers.2.mlp.experts.1.down_proj.weight": "model-00004-of-00039.safetensors", "model.layers.2.mlp.experts.2.down_proj.weight": "model-00004-of-00039.safetensors", "model.layers.2.mlp.experts.3.down_proj.weight": "model-00004-of-00039.safetensors", "model.layers.2.mlp.shared_expert.down_proj.weight": "model-00004-of-00039.safetensors", "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00005-of-00039.safetensors", "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00005-of-00039.safetensors", "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00005-of-00039.safetensors", "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00005-of-00039.safetensors", "model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00005-of-00039.safetensors", "model.layers.2.mlp.experts.0.up_proj.weight": "model-00005-of-00039.safetensors", "model.layers.2.mlp.experts.1.up_proj.weight": "model-00005-of-00039.safetensors", "model.layers.2.mlp.experts.2.up_proj.weight": "model-00005-of-00039.safetensors", "model.layers.2.mlp.experts.3.up_proj.weight": "model-00005-of-00039.safetensors", "model.layers.2.mlp.shared_expert.up_proj.weight": "model-00005-of-00039.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00039.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00005-of-00039.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00039.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00039.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00005-of-00039.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00039.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00005-of-00039.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00039.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00039.safetensors", "model.layers.3.mlp.experts.0.down_proj.weight": "model-00005-of-00039.safetensors", "model.layers.3.mlp.experts.1.down_proj.weight": "model-00006-of-00039.safetensors", "model.layers.3.mlp.experts.2.down_proj.weight": "model-00006-of-00039.safetensors", "model.layers.3.mlp.experts.3.down_proj.weight": "model-00006-of-00039.safetensors", "model.layers.3.mlp.shared_expert.down_proj.weight": "model-00006-of-00039.safetensors", "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00006-of-00039.safetensors", "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00006-of-00039.safetensors", "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00006-of-00039.safetensors", "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00006-of-00039.safetensors", "model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00006-of-00039.safetensors", "model.layers.3.mlp.experts.0.up_proj.weight": "model-00006-of-00039.safetensors", "model.layers.3.mlp.experts.1.up_proj.weight": "model-00006-of-00039.safetensors", "model.layers.3.mlp.experts.2.up_proj.weight": "model-00006-of-00039.safetensors", "model.layers.3.mlp.experts.3.up_proj.weight": "model-00006-of-00039.safetensors", "model.layers.3.mlp.shared_expert.up_proj.weight": "model-00007-of-00039.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00039.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00007-of-00039.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00039.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00039.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00007-of-00039.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00039.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00007-of-00039.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00039.safetensors", "model.layers.4.input_layernorm.weight": "model-00007-of-00039.safetensors", "model.layers.4.mlp.experts.0.down_proj.weight": "model-00007-of-00039.safetensors", "model.layers.4.mlp.experts.1.down_proj.weight": "model-00007-of-00039.safetensors", "model.layers.4.mlp.experts.2.down_proj.weight": "model-00007-of-00039.safetensors", "model.layers.4.mlp.experts.3.down_proj.weight": "model-00007-of-00039.safetensors", "model.layers.4.mlp.shared_expert.down_proj.weight": "model-00007-of-00039.safetensors", "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00007-of-00039.safetensors", "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00007-of-00039.safetensors", "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00007-of-00039.safetensors", "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00007-of-00039.safetensors", "model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00007-of-00039.safetensors", "model.layers.4.mlp.experts.0.up_proj.weight": "model-00008-of-00039.safetensors", "model.layers.4.mlp.experts.1.up_proj.weight": "model-00008-of-00039.safetensors", "model.layers.4.mlp.experts.2.up_proj.weight": "model-00008-of-00039.safetensors", "model.layers.4.mlp.experts.3.up_proj.weight": "model-00008-of-00039.safetensors", "model.layers.4.mlp.shared_expert.up_proj.weight": "model-00008-of-00039.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00039.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00008-of-00039.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00039.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00039.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00008-of-00039.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00039.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00008-of-00039.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00039.safetensors", "model.layers.5.input_layernorm.weight": "model-00008-of-00039.safetensors", "model.layers.5.mlp.experts.0.down_proj.weight": "model-00008-of-00039.safetensors", "model.layers.5.mlp.experts.1.down_proj.weight": "model-00008-of-00039.safetensors", "model.layers.5.mlp.experts.2.down_proj.weight": "model-00008-of-00039.safetensors", "model.layers.5.mlp.experts.3.down_proj.weight": "model-00008-of-00039.safetensors", "model.layers.5.mlp.shared_expert.down_proj.weight": "model-00008-of-00039.safetensors", "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00008-of-00039.safetensors", "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00009-of-00039.safetensors", "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00009-of-00039.safetensors", "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00009-of-00039.safetensors", "model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00009-of-00039.safetensors", "model.layers.5.mlp.experts.0.up_proj.weight": "model-00009-of-00039.safetensors", "model.layers.5.mlp.experts.1.up_proj.weight": "model-00009-of-00039.safetensors", "model.layers.5.mlp.experts.2.up_proj.weight": "model-00009-of-00039.safetensors", "model.layers.5.mlp.experts.3.up_proj.weight": "model-00009-of-00039.safetensors", "model.layers.5.mlp.shared_expert.up_proj.weight": "model-00009-of-00039.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00039.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00009-of-00039.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00009-of-00039.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00009-of-00039.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00009-of-00039.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00009-of-00039.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00009-of-00039.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00009-of-00039.safetensors", "model.layers.6.input_layernorm.weight": "model-00009-of-00039.safetensors", "model.layers.6.mlp.experts.0.down_proj.weight": "model-00009-of-00039.safetensors", "model.layers.6.mlp.experts.1.down_proj.weight": "model-00009-of-00039.safetensors", "model.layers.6.mlp.experts.2.down_proj.weight": "model-00009-of-00039.safetensors", "model.layers.6.mlp.experts.3.down_proj.weight": "model-00009-of-00039.safetensors", "model.layers.6.mlp.shared_expert.down_proj.weight": "model-00010-of-00039.safetensors", "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00010-of-00039.safetensors", "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00010-of-00039.safetensors", "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00010-of-00039.safetensors", "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00010-of-00039.safetensors", "model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00010-of-00039.safetensors", "model.layers.6.mlp.experts.0.up_proj.weight": "model-00010-of-00039.safetensors", "model.layers.6.mlp.experts.1.up_proj.weight": "model-00010-of-00039.safetensors", "model.layers.6.mlp.experts.2.up_proj.weight": "model-00010-of-00039.safetensors", "model.layers.6.mlp.experts.3.up_proj.weight": "model-00010-of-00039.safetensors", "model.layers.6.mlp.shared_expert.up_proj.weight": "model-00010-of-00039.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00039.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00010-of-00039.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00039.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00039.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00010-of-00039.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00039.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00010-of-00039.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00039.safetensors", "model.layers.7.input_layernorm.weight": "model-00010-of-00039.safetensors", "model.layers.7.mlp.experts.0.down_proj.weight": "model-00011-of-00039.safetensors", "model.layers.7.mlp.experts.1.down_proj.weight": "model-00011-of-00039.safetensors", "model.layers.7.mlp.experts.2.down_proj.weight": "model-00011-of-00039.safetensors", "model.layers.7.mlp.experts.3.down_proj.weight": "model-00011-of-00039.safetensors", "model.layers.7.mlp.shared_expert.down_proj.weight": "model-00011-of-00039.safetensors", "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00011-of-00039.safetensors", "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00011-of-00039.safetensors", "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00011-of-00039.safetensors", "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00011-of-00039.safetensors", "model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00011-of-00039.safetensors", "model.layers.7.mlp.experts.0.up_proj.weight": "model-00011-of-00039.safetensors", "model.layers.7.mlp.experts.1.up_proj.weight": "model-00011-of-00039.safetensors", "model.layers.7.mlp.experts.2.up_proj.weight": "model-00011-of-00039.safetensors", "model.layers.7.mlp.experts.3.up_proj.weight": "model-00012-of-00039.safetensors", "model.layers.7.mlp.shared_expert.up_proj.weight": "model-00012-of-00039.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00012-of-00039.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00012-of-00039.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00012-of-00039.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00012-of-00039.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00012-of-00039.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00012-of-00039.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00012-of-00039.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00012-of-00039.safetensors", "model.layers.8.input_layernorm.weight": "model-00012-of-00039.safetensors", "model.layers.8.mlp.experts.0.down_proj.weight": "model-00012-of-00039.safetensors", "model.layers.8.mlp.experts.1.down_proj.weight": "model-00012-of-00039.safetensors", "model.layers.8.mlp.experts.2.down_proj.weight": "model-00012-of-00039.safetensors", "model.layers.8.mlp.experts.3.down_proj.weight": "model-00012-of-00039.safetensors", "model.layers.8.mlp.shared_expert.down_proj.weight": "model-00012-of-00039.safetensors", "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00012-of-00039.safetensors", "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00012-of-00039.safetensors", "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00012-of-00039.safetensors", "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00012-of-00039.safetensors", "model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00013-of-00039.safetensors", "model.layers.8.mlp.experts.0.up_proj.weight": "model-00013-of-00039.safetensors", "model.layers.8.mlp.experts.1.up_proj.weight": "model-00013-of-00039.safetensors", "model.layers.8.mlp.experts.2.up_proj.weight": "model-00013-of-00039.safetensors", "model.layers.8.mlp.experts.3.up_proj.weight": "model-00013-of-00039.safetensors", "model.layers.8.mlp.shared_expert.up_proj.weight": "model-00013-of-00039.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00013-of-00039.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00013-of-00039.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00013-of-00039.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00013-of-00039.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00013-of-00039.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00013-of-00039.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00013-of-00039.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00013-of-00039.safetensors", "model.layers.9.input_layernorm.weight": "model-00013-of-00039.safetensors", "model.layers.9.mlp.experts.0.down_proj.weight": "model-00013-of-00039.safetensors", "model.layers.9.mlp.experts.1.down_proj.weight": "model-00013-of-00039.safetensors", "model.layers.9.mlp.experts.2.down_proj.weight": "model-00013-of-00039.safetensors", "model.layers.9.mlp.experts.3.down_proj.weight": "model-00013-of-00039.safetensors", "model.layers.9.mlp.shared_expert.down_proj.weight": "model-00013-of-00039.safetensors", "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00014-of-00039.safetensors", "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00014-of-00039.safetensors", "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00014-of-00039.safetensors", "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00014-of-00039.safetensors", "model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00014-of-00039.safetensors", "model.layers.9.mlp.experts.0.up_proj.weight": "model-00014-of-00039.safetensors", "model.layers.9.mlp.experts.1.up_proj.weight": "model-00014-of-00039.safetensors", "model.layers.9.mlp.experts.2.up_proj.weight": "model-00014-of-00039.safetensors", "model.layers.9.mlp.experts.3.up_proj.weight": "model-00014-of-00039.safetensors", "model.layers.9.mlp.shared_expert.up_proj.weight": "model-00014-of-00039.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00039.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00014-of-00039.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00039.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00039.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00014-of-00039.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00039.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00014-of-00039.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00039.safetensors", "model.layers.10.input_layernorm.weight": "model-00014-of-00039.safetensors", "model.layers.10.mlp.experts.0.down_proj.weight": "model-00014-of-00039.safetensors", "model.layers.10.mlp.experts.1.down_proj.weight": "model-00015-of-00039.safetensors", "model.layers.10.mlp.experts.2.down_proj.weight": "model-00015-of-00039.safetensors", "model.layers.10.mlp.experts.3.down_proj.weight": "model-00015-of-00039.safetensors", "model.layers.10.mlp.shared_expert.down_proj.weight": "model-00015-of-00039.safetensors", "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00015-of-00039.safetensors", "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00015-of-00039.safetensors", "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00015-of-00039.safetensors", "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00015-of-00039.safetensors", "model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00015-of-00039.safetensors", "model.layers.10.mlp.experts.0.up_proj.weight": "model-00015-of-00039.safetensors", "model.layers.10.mlp.experts.1.up_proj.weight": "model-00015-of-00039.safetensors", "model.layers.10.mlp.experts.2.up_proj.weight": "model-00015-of-00039.safetensors", "model.layers.10.mlp.experts.3.up_proj.weight": "model-00015-of-00039.safetensors", "model.layers.10.mlp.shared_expert.up_proj.weight": "model-00016-of-00039.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00016-of-00039.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00016-of-00039.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00016-of-00039.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00016-of-00039.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00016-of-00039.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00016-of-00039.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00016-of-00039.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00016-of-00039.safetensors", "model.layers.11.input_layernorm.weight": "model-00016-of-00039.safetensors", "model.layers.11.mlp.experts.0.down_proj.weight": "model-00016-of-00039.safetensors", "model.layers.11.mlp.experts.1.down_proj.weight": "model-00016-of-00039.safetensors", "model.layers.11.mlp.experts.2.down_proj.weight": "model-00016-of-00039.safetensors", "model.layers.11.mlp.experts.3.down_proj.weight": "model-00016-of-00039.safetensors", "model.layers.11.mlp.shared_expert.down_proj.weight": "model-00016-of-00039.safetensors", "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00016-of-00039.safetensors", "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00016-of-00039.safetensors", "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00016-of-00039.safetensors", "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00016-of-00039.safetensors", "model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00016-of-00039.safetensors", "model.layers.11.mlp.experts.0.up_proj.weight": "model-00017-of-00039.safetensors", "model.layers.11.mlp.experts.1.up_proj.weight": "model-00017-of-00039.safetensors", "model.layers.11.mlp.experts.2.up_proj.weight": "model-00017-of-00039.safetensors", "model.layers.11.mlp.experts.3.up_proj.weight": "model-00017-of-00039.safetensors", "model.layers.11.mlp.shared_expert.up_proj.weight": "model-00017-of-00039.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00017-of-00039.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00017-of-00039.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00017-of-00039.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00017-of-00039.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00017-of-00039.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00017-of-00039.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00017-of-00039.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00017-of-00039.safetensors", "model.layers.12.input_layernorm.weight": "model-00017-of-00039.safetensors", "model.layers.12.mlp.experts.0.down_proj.weight": "model-00017-of-00039.safetensors", "model.layers.12.mlp.experts.1.down_proj.weight": "model-00017-of-00039.safetensors", "model.layers.12.mlp.experts.2.down_proj.weight": "model-00017-of-00039.safetensors", "model.layers.12.mlp.experts.3.down_proj.weight": "model-00017-of-00039.safetensors", "model.layers.12.mlp.shared_expert.down_proj.weight": "model-00017-of-00039.safetensors", "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00017-of-00039.safetensors", "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00018-of-00039.safetensors", "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00018-of-00039.safetensors", "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00018-of-00039.safetensors", "model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00018-of-00039.safetensors", "model.layers.12.mlp.experts.0.up_proj.weight": "model-00018-of-00039.safetensors", "model.layers.12.mlp.experts.1.up_proj.weight": "model-00018-of-00039.safetensors", "model.layers.12.mlp.experts.2.up_proj.weight": "model-00018-of-00039.safetensors", "model.layers.12.mlp.experts.3.up_proj.weight": "model-00018-of-00039.safetensors", "model.layers.12.mlp.shared_expert.up_proj.weight": "model-00018-of-00039.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00018-of-00039.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00018-of-00039.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00018-of-00039.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00018-of-00039.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00018-of-00039.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00018-of-00039.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00018-of-00039.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00018-of-00039.safetensors", "model.layers.13.input_layernorm.weight": "model-00018-of-00039.safetensors", "model.layers.13.mlp.experts.0.down_proj.weight": "model-00018-of-00039.safetensors", "model.layers.13.mlp.experts.1.down_proj.weight": "model-00018-of-00039.safetensors", "model.layers.13.mlp.experts.2.down_proj.weight": "model-00018-of-00039.safetensors", "model.layers.13.mlp.experts.3.down_proj.weight": "model-00018-of-00039.safetensors", "model.layers.13.mlp.shared_expert.down_proj.weight": "model-00019-of-00039.safetensors", "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00019-of-00039.safetensors", "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00019-of-00039.safetensors", "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00019-of-00039.safetensors", "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00019-of-00039.safetensors", "model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00019-of-00039.safetensors", "model.layers.13.mlp.experts.0.up_proj.weight": "model-00019-of-00039.safetensors", "model.layers.13.mlp.experts.1.up_proj.weight": "model-00019-of-00039.safetensors", "model.layers.13.mlp.experts.2.up_proj.weight": "model-00019-of-00039.safetensors", "model.layers.13.mlp.experts.3.up_proj.weight": "model-00019-of-00039.safetensors", "model.layers.13.mlp.shared_expert.up_proj.weight": "model-00019-of-00039.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00019-of-00039.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00019-of-00039.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00019-of-00039.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00019-of-00039.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00019-of-00039.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00019-of-00039.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00019-of-00039.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00019-of-00039.safetensors", "model.layers.14.input_layernorm.weight": "model-00019-of-00039.safetensors", "model.layers.14.mlp.experts.0.down_proj.weight": "model-00020-of-00039.safetensors", "model.layers.14.mlp.experts.1.down_proj.weight": "model-00020-of-00039.safetensors", "model.layers.14.mlp.experts.2.down_proj.weight": "model-00020-of-00039.safetensors", "model.layers.14.mlp.experts.3.down_proj.weight": "model-00020-of-00039.safetensors", "model.layers.14.mlp.shared_expert.down_proj.weight": "model-00020-of-00039.safetensors", "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00020-of-00039.safetensors", "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00020-of-00039.safetensors", "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00020-of-00039.safetensors", "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00020-of-00039.safetensors", "model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00020-of-00039.safetensors", "model.layers.14.mlp.experts.0.up_proj.weight": "model-00020-of-00039.safetensors", "model.layers.14.mlp.experts.1.up_proj.weight": "model-00020-of-00039.safetensors", "model.layers.14.mlp.experts.2.up_proj.weight": "model-00020-of-00039.safetensors", "model.layers.14.mlp.experts.3.up_proj.weight": "model-00021-of-00039.safetensors", "model.layers.14.mlp.shared_expert.up_proj.weight": "model-00021-of-00039.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00021-of-00039.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00021-of-00039.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00021-of-00039.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00021-of-00039.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00021-of-00039.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00021-of-00039.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00021-of-00039.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00021-of-00039.safetensors", "model.layers.15.input_layernorm.weight": "model-00021-of-00039.safetensors", "model.layers.15.mlp.experts.0.down_proj.weight": "model-00021-of-00039.safetensors", "model.layers.15.mlp.experts.1.down_proj.weight": "model-00021-of-00039.safetensors", "model.layers.15.mlp.experts.2.down_proj.weight": "model-00021-of-00039.safetensors", "model.layers.15.mlp.experts.3.down_proj.weight": "model-00021-of-00039.safetensors", "model.layers.15.mlp.shared_expert.down_proj.weight": "model-00021-of-00039.safetensors", "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00021-of-00039.safetensors", "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00021-of-00039.safetensors", "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00021-of-00039.safetensors", "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00021-of-00039.safetensors", "model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00022-of-00039.safetensors", "model.layers.15.mlp.experts.0.up_proj.weight": "model-00022-of-00039.safetensors", "model.layers.15.mlp.experts.1.up_proj.weight": "model-00022-of-00039.safetensors", "model.layers.15.mlp.experts.2.up_proj.weight": "model-00022-of-00039.safetensors", "model.layers.15.mlp.experts.3.up_proj.weight": "model-00022-of-00039.safetensors", "model.layers.15.mlp.shared_expert.up_proj.weight": "model-00022-of-00039.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00022-of-00039.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00022-of-00039.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00022-of-00039.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00022-of-00039.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00022-of-00039.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00022-of-00039.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00022-of-00039.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00022-of-00039.safetensors", "model.layers.16.input_layernorm.weight": "model-00022-of-00039.safetensors", "model.layers.16.mlp.experts.0.down_proj.weight": "model-00022-of-00039.safetensors", "model.layers.16.mlp.experts.1.down_proj.weight": "model-00022-of-00039.safetensors", "model.layers.16.mlp.experts.2.down_proj.weight": "model-00022-of-00039.safetensors", "model.layers.16.mlp.experts.3.down_proj.weight": "model-00022-of-00039.safetensors", "model.layers.16.mlp.shared_expert.down_proj.weight": "model-00022-of-00039.safetensors", "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00023-of-00039.safetensors", "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00023-of-00039.safetensors", "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00023-of-00039.safetensors", "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00023-of-00039.safetensors", "model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00023-of-00039.safetensors", "model.layers.16.mlp.experts.0.up_proj.weight": "model-00023-of-00039.safetensors", "model.layers.16.mlp.experts.1.up_proj.weight": "model-00023-of-00039.safetensors", "model.layers.16.mlp.experts.2.up_proj.weight": "model-00023-of-00039.safetensors", "model.layers.16.mlp.experts.3.up_proj.weight": "model-00023-of-00039.safetensors", "model.layers.16.mlp.shared_expert.up_proj.weight": "model-00023-of-00039.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00023-of-00039.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00023-of-00039.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00023-of-00039.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00023-of-00039.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00023-of-00039.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00023-of-00039.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00023-of-00039.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00023-of-00039.safetensors", "model.layers.17.input_layernorm.weight": "model-00023-of-00039.safetensors", "model.layers.17.mlp.experts.0.down_proj.weight": "model-00023-of-00039.safetensors", "model.layers.17.mlp.experts.1.down_proj.weight": "model-00024-of-00039.safetensors", "model.layers.17.mlp.experts.2.down_proj.weight": "model-00024-of-00039.safetensors", "model.layers.17.mlp.experts.3.down_proj.weight": "model-00024-of-00039.safetensors", "model.layers.17.mlp.shared_expert.down_proj.weight": "model-00024-of-00039.safetensors", "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00024-of-00039.safetensors", "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00024-of-00039.safetensors", "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00024-of-00039.safetensors", "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00024-of-00039.safetensors", "model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00024-of-00039.safetensors", "model.layers.17.mlp.experts.0.up_proj.weight": "model-00024-of-00039.safetensors", "model.layers.17.mlp.experts.1.up_proj.weight": "model-00024-of-00039.safetensors", "model.layers.17.mlp.experts.2.up_proj.weight": "model-00024-of-00039.safetensors", "model.layers.17.mlp.experts.3.up_proj.weight": "model-00024-of-00039.safetensors", "model.layers.17.mlp.shared_expert.up_proj.weight": "model-00025-of-00039.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00025-of-00039.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00025-of-00039.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00025-of-00039.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00025-of-00039.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00025-of-00039.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00025-of-00039.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00025-of-00039.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00025-of-00039.safetensors", "model.layers.18.input_layernorm.weight": "model-00025-of-00039.safetensors", "model.layers.18.mlp.experts.0.down_proj.weight": "model-00025-of-00039.safetensors", "model.layers.18.mlp.experts.1.down_proj.weight": "model-00025-of-00039.safetensors", "model.layers.18.mlp.experts.2.down_proj.weight": "model-00025-of-00039.safetensors", "model.layers.18.mlp.experts.3.down_proj.weight": "model-00025-of-00039.safetensors", "model.layers.18.mlp.shared_expert.down_proj.weight": "model-00025-of-00039.safetensors", "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00025-of-00039.safetensors", "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00025-of-00039.safetensors", "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00025-of-00039.safetensors", "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00025-of-00039.safetensors", "model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00025-of-00039.safetensors", "model.layers.18.mlp.experts.0.up_proj.weight": "model-00026-of-00039.safetensors", "model.layers.18.mlp.experts.1.up_proj.weight": "model-00026-of-00039.safetensors", "model.layers.18.mlp.experts.2.up_proj.weight": "model-00026-of-00039.safetensors", "model.layers.18.mlp.experts.3.up_proj.weight": "model-00026-of-00039.safetensors", "model.layers.18.mlp.shared_expert.up_proj.weight": "model-00026-of-00039.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00026-of-00039.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00026-of-00039.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00026-of-00039.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00026-of-00039.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00026-of-00039.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00026-of-00039.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00026-of-00039.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00026-of-00039.safetensors", "model.layers.19.input_layernorm.weight": "model-00026-of-00039.safetensors", "model.layers.19.mlp.experts.0.down_proj.weight": "model-00026-of-00039.safetensors", "model.layers.19.mlp.experts.1.down_proj.weight": "model-00026-of-00039.safetensors", "model.layers.19.mlp.experts.2.down_proj.weight": "model-00026-of-00039.safetensors", "model.layers.19.mlp.experts.3.down_proj.weight": "model-00026-of-00039.safetensors", "model.layers.19.mlp.shared_expert.down_proj.weight": "model-00026-of-00039.safetensors", "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00026-of-00039.safetensors", "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00027-of-00039.safetensors", "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00027-of-00039.safetensors", "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00027-of-00039.safetensors", "model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00027-of-00039.safetensors", "model.layers.19.mlp.experts.0.up_proj.weight": "model-00027-of-00039.safetensors", "model.layers.19.mlp.experts.1.up_proj.weight": "model-00027-of-00039.safetensors", "model.layers.19.mlp.experts.2.up_proj.weight": "model-00027-of-00039.safetensors", "model.layers.19.mlp.experts.3.up_proj.weight": "model-00027-of-00039.safetensors", "model.layers.19.mlp.shared_expert.up_proj.weight": "model-00027-of-00039.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00027-of-00039.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00027-of-00039.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00027-of-00039.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00027-of-00039.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00027-of-00039.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00027-of-00039.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00027-of-00039.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00027-of-00039.safetensors", "model.layers.20.input_layernorm.weight": "model-00027-of-00039.safetensors", "model.layers.20.mlp.experts.0.down_proj.weight": "model-00027-of-00039.safetensors", "model.layers.20.mlp.experts.1.down_proj.weight": "model-00027-of-00039.safetensors", "model.layers.20.mlp.experts.2.down_proj.weight": "model-00027-of-00039.safetensors", "model.layers.20.mlp.experts.3.down_proj.weight": "model-00027-of-00039.safetensors", "model.layers.20.mlp.shared_expert.down_proj.weight": "model-00028-of-00039.safetensors", "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00028-of-00039.safetensors", "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00028-of-00039.safetensors", "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00028-of-00039.safetensors", "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00028-of-00039.safetensors", "model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00028-of-00039.safetensors", "model.layers.20.mlp.experts.0.up_proj.weight": "model-00028-of-00039.safetensors", "model.layers.20.mlp.experts.1.up_proj.weight": "model-00028-of-00039.safetensors", "model.layers.20.mlp.experts.2.up_proj.weight": "model-00028-of-00039.safetensors", "model.layers.20.mlp.experts.3.up_proj.weight": "model-00028-of-00039.safetensors", "model.layers.20.mlp.shared_expert.up_proj.weight": "model-00028-of-00039.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00028-of-00039.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00028-of-00039.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00028-of-00039.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00028-of-00039.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00028-of-00039.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00028-of-00039.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00028-of-00039.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00028-of-00039.safetensors", "model.layers.21.input_layernorm.weight": "model-00028-of-00039.safetensors", "model.layers.21.mlp.experts.0.down_proj.weight": "model-00029-of-00039.safetensors", "model.layers.21.mlp.experts.1.down_proj.weight": "model-00029-of-00039.safetensors", "model.layers.21.mlp.experts.2.down_proj.weight": "model-00029-of-00039.safetensors", "model.layers.21.mlp.experts.3.down_proj.weight": "model-00029-of-00039.safetensors", "model.layers.21.mlp.shared_expert.down_proj.weight": "model-00029-of-00039.safetensors", "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00029-of-00039.safetensors", "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00029-of-00039.safetensors", "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00029-of-00039.safetensors", "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00029-of-00039.safetensors", "model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00029-of-00039.safetensors", "model.layers.21.mlp.experts.0.up_proj.weight": "model-00029-of-00039.safetensors", "model.layers.21.mlp.experts.1.up_proj.weight": "model-00029-of-00039.safetensors", "model.layers.21.mlp.experts.2.up_proj.weight": "model-00029-of-00039.safetensors", "model.layers.21.mlp.experts.3.up_proj.weight": "model-00030-of-00039.safetensors", "model.layers.21.mlp.shared_expert.up_proj.weight": "model-00030-of-00039.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00030-of-00039.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00030-of-00039.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00030-of-00039.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00030-of-00039.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00030-of-00039.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00030-of-00039.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00030-of-00039.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00030-of-00039.safetensors", "model.layers.22.input_layernorm.weight": "model-00030-of-00039.safetensors", "model.layers.22.mlp.experts.0.down_proj.weight": "model-00030-of-00039.safetensors", "model.layers.22.mlp.experts.1.down_proj.weight": "model-00030-of-00039.safetensors", "model.layers.22.mlp.experts.2.down_proj.weight": "model-00030-of-00039.safetensors", "model.layers.22.mlp.experts.3.down_proj.weight": "model-00030-of-00039.safetensors", "model.layers.22.mlp.shared_expert.down_proj.weight": "model-00030-of-00039.safetensors", "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00030-of-00039.safetensors", "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00030-of-00039.safetensors", "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00030-of-00039.safetensors", "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00030-of-00039.safetensors", "model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00031-of-00039.safetensors", "model.layers.22.mlp.experts.0.up_proj.weight": "model-00031-of-00039.safetensors", "model.layers.22.mlp.experts.1.up_proj.weight": "model-00031-of-00039.safetensors", "model.layers.22.mlp.experts.2.up_proj.weight": "model-00031-of-00039.safetensors", "model.layers.22.mlp.experts.3.up_proj.weight": "model-00031-of-00039.safetensors", "model.layers.22.mlp.shared_expert.up_proj.weight": "model-00031-of-00039.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00031-of-00039.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00031-of-00039.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00031-of-00039.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00031-of-00039.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00031-of-00039.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00031-of-00039.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00031-of-00039.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00031-of-00039.safetensors", "model.layers.23.input_layernorm.weight": "model-00031-of-00039.safetensors", "model.layers.23.mlp.experts.0.down_proj.weight": "model-00031-of-00039.safetensors", "model.layers.23.mlp.experts.1.down_proj.weight": "model-00031-of-00039.safetensors", "model.layers.23.mlp.experts.2.down_proj.weight": "model-00031-of-00039.safetensors", "model.layers.23.mlp.experts.3.down_proj.weight": "model-00031-of-00039.safetensors", "model.layers.23.mlp.shared_expert.down_proj.weight": "model-00031-of-00039.safetensors", "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00032-of-00039.safetensors", "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00032-of-00039.safetensors", "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00032-of-00039.safetensors", "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00032-of-00039.safetensors", "model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00032-of-00039.safetensors", "model.layers.23.mlp.experts.0.up_proj.weight": "model-00032-of-00039.safetensors", "model.layers.23.mlp.experts.1.up_proj.weight": "model-00032-of-00039.safetensors", "model.layers.23.mlp.experts.2.up_proj.weight": "model-00032-of-00039.safetensors", "model.layers.23.mlp.experts.3.up_proj.weight": "model-00032-of-00039.safetensors", "model.layers.23.mlp.shared_expert.up_proj.weight": "model-00032-of-00039.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00032-of-00039.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00032-of-00039.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00032-of-00039.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00032-of-00039.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00032-of-00039.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00032-of-00039.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00032-of-00039.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00032-of-00039.safetensors", "model.layers.24.input_layernorm.weight": "model-00032-of-00039.safetensors", "model.layers.24.mlp.experts.0.down_proj.weight": "model-00032-of-00039.safetensors", "model.layers.24.mlp.experts.1.down_proj.weight": "model-00033-of-00039.safetensors", "model.layers.24.mlp.experts.2.down_proj.weight": "model-00033-of-00039.safetensors", "model.layers.24.mlp.experts.3.down_proj.weight": "model-00033-of-00039.safetensors", "model.layers.24.mlp.shared_expert.down_proj.weight": "model-00033-of-00039.safetensors", "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00033-of-00039.safetensors", "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00033-of-00039.safetensors", "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00033-of-00039.safetensors", "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00033-of-00039.safetensors", "model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00033-of-00039.safetensors", "model.layers.24.mlp.experts.0.up_proj.weight": "model-00033-of-00039.safetensors", "model.layers.24.mlp.experts.1.up_proj.weight": "model-00033-of-00039.safetensors", "model.layers.24.mlp.experts.2.up_proj.weight": "model-00033-of-00039.safetensors", "model.layers.24.mlp.experts.3.up_proj.weight": "model-00033-of-00039.safetensors", "model.layers.24.mlp.shared_expert.up_proj.weight": "model-00034-of-00039.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00034-of-00039.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00034-of-00039.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00034-of-00039.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00034-of-00039.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00034-of-00039.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00034-of-00039.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00034-of-00039.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00034-of-00039.safetensors", "model.layers.25.input_layernorm.weight": "model-00034-of-00039.safetensors", "model.layers.25.mlp.experts.0.down_proj.weight": "model-00034-of-00039.safetensors", "model.layers.25.mlp.experts.1.down_proj.weight": "model-00034-of-00039.safetensors", "model.layers.25.mlp.experts.2.down_proj.weight": "model-00034-of-00039.safetensors", "model.layers.25.mlp.experts.3.down_proj.weight": "model-00034-of-00039.safetensors", "model.layers.25.mlp.shared_expert.down_proj.weight": "model-00034-of-00039.safetensors", "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00034-of-00039.safetensors", "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00034-of-00039.safetensors", "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00034-of-00039.safetensors", "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00034-of-00039.safetensors", "model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00034-of-00039.safetensors", "model.layers.25.mlp.experts.0.up_proj.weight": "model-00035-of-00039.safetensors", "model.layers.25.mlp.experts.1.up_proj.weight": "model-00035-of-00039.safetensors", "model.layers.25.mlp.experts.2.up_proj.weight": "model-00035-of-00039.safetensors", "model.layers.25.mlp.experts.3.up_proj.weight": "model-00035-of-00039.safetensors", "model.layers.25.mlp.shared_expert.up_proj.weight": "model-00035-of-00039.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00035-of-00039.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00035-of-00039.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00035-of-00039.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00035-of-00039.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00035-of-00039.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00035-of-00039.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00035-of-00039.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00035-of-00039.safetensors", "model.layers.26.input_layernorm.weight": "model-00035-of-00039.safetensors", "model.layers.26.mlp.experts.0.down_proj.weight": "model-00035-of-00039.safetensors", "model.layers.26.mlp.experts.1.down_proj.weight": "model-00035-of-00039.safetensors", "model.layers.26.mlp.experts.2.down_proj.weight": "model-00035-of-00039.safetensors", "model.layers.26.mlp.experts.3.down_proj.weight": "model-00035-of-00039.safetensors", "model.layers.26.mlp.shared_expert.down_proj.weight": "model-00035-of-00039.safetensors", "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00035-of-00039.safetensors", "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00036-of-00039.safetensors", "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00036-of-00039.safetensors", "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00036-of-00039.safetensors", "model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00036-of-00039.safetensors", "model.layers.26.mlp.experts.0.up_proj.weight": "model-00036-of-00039.safetensors", "model.layers.26.mlp.experts.1.up_proj.weight": "model-00036-of-00039.safetensors", "model.layers.26.mlp.experts.2.up_proj.weight": "model-00036-of-00039.safetensors", "model.layers.26.mlp.experts.3.up_proj.weight": "model-00036-of-00039.safetensors", "model.layers.26.mlp.shared_expert.up_proj.weight": "model-00036-of-00039.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00036-of-00039.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00036-of-00039.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00036-of-00039.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00036-of-00039.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00036-of-00039.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00036-of-00039.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00036-of-00039.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00036-of-00039.safetensors", "model.layers.27.input_layernorm.weight": "model-00036-of-00039.safetensors", "model.layers.27.mlp.experts.0.down_proj.weight": "model-00036-of-00039.safetensors", "model.layers.27.mlp.experts.1.down_proj.weight": "model-00036-of-00039.safetensors", "model.layers.27.mlp.experts.2.down_proj.weight": "model-00036-of-00039.safetensors", "model.layers.27.mlp.experts.3.down_proj.weight": "model-00036-of-00039.safetensors", "model.layers.27.mlp.shared_expert.down_proj.weight": "model-00037-of-00039.safetensors", "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00037-of-00039.safetensors", "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00037-of-00039.safetensors", "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00037-of-00039.safetensors", "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00037-of-00039.safetensors", "model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00037-of-00039.safetensors", "model.layers.27.mlp.experts.0.up_proj.weight": "model-00037-of-00039.safetensors", "model.layers.27.mlp.experts.1.up_proj.weight": "model-00037-of-00039.safetensors", "model.layers.27.mlp.experts.2.up_proj.weight": "model-00037-of-00039.safetensors", "model.layers.27.mlp.experts.3.up_proj.weight": "model-00037-of-00039.safetensors", "model.layers.27.mlp.shared_expert.up_proj.weight": "model-00037-of-00039.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00037-of-00039.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00037-of-00039.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00037-of-00039.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00037-of-00039.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00037-of-00039.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00037-of-00039.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00037-of-00039.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00037-of-00039.safetensors", "model.norm.weight": "model-00037-of-00039.safetensors", "lm_head.weight": "model-00038-of-00039.safetensors", "model.layers.0.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.0.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.1.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.1.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.2.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.2.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.3.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.3.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.4.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.4.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.5.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.5.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.6.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.6.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.7.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.7.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.8.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.8.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.9.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.9.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.10.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.10.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.11.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.11.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.12.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.12.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.13.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.13.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.14.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.14.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.15.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.15.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.16.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.16.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.17.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.17.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.18.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.18.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.19.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.19.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.20.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.20.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.21.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.21.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.22.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.22.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.23.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.23.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.24.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.24.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.25.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.25.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.26.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.26.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors", "model.layers.27.mlp.gate.weight": "model-00039-of-00039.safetensors", "model.layers.27.mlp.shared_expert_gate.weight": "model-00039-of-00039.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a2951d5edfa5cc0a2346ef872f8c77a2920274cfc3b503b04e3799104dee80
+size 11422060

tokenizer_config.json

@@ -0,0 +1,211 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "max_length": null,
+  "model_max_length": 131072,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|im_end|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}