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": "Orion-zhen/Meissa-Qwen2.5-7B-Instruct",
+  "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": 5,
+  "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 +1,23 @@
+
+base_model: Orion-zhen/Meissa-Qwen2.5-7B-Instruct
+architecture: qwen
+gate_mode: hidden
+dtype: bfloat16
+experts:
+  - source_model: Orion-zhen/Meissa-Qwen2.5-7B-Instruct
+    positive_prompts: ["chat", "assistant", "chat history", "chat context", "writing", "text writing", "editing", "text editing", "multilingual"]
+  - source_model: Qwen/Qwen2.5-Math-1.5B
+    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"]
+  - source_model: Kukedlc/Qwen2.5-1.5B-Spanish-1.0-DPO
+    positive_prompts: ["spanis chat", "spanish chatting", "spanish", "spanish language", "spanish text writing/editing"]
+shared_experts:
+  - source_model: Orion-zhen/Meissa-Qwen2.5-7B-Instruct
+    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-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7750ef811855400eaf0017804c4c12081ba254debbfcf4a3235384784c5a429
+size 1089994896

model-00002-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ed9a499613019374ed007126167110c6c269f833cea30c605e8766527a6df8b
+size 996942656

model-00003-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff32ac545d7165eba21aa42685a17211a28d65e0ab03125468c06692803cdbd0
+size 982542024

model-00004-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55ad42e0ee680045269ef2fd377119dea4fc2996de834cc5e3a41bd6ce620056
+size 919889480

model-00005-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3241023611839d30d0ce51ce15118c964425bfea0cdc28e2d473aabdf75d5c
+size 998786192

model-00006-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b57258d5e9819ca1adcc797aae151543dc956f2a166395f0aa5cf9a52ebe724
+size 998778904

model-00007-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a0182bbec5683b343300ebaa729393cbe4332a11a300fa1442dc29266da6204
+size 964978368

model-00008-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73bb643ba028403e2af2756ff7e8f713b3634877303d3ae9058aaa87100cbcb5
+size 964978368

model-00009-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec2e5a93bf196b2502bbc9cc6b41d0e282d30eeaa27f128b9281e0ead819c41b
+size 998786192

model-00010-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cf758de680822a397853d5b3aa2f90ed0e4c1fe5772a835f399900f4767ccb3
+size 998778904

model-00011-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c80e9f86813b6327a7ebed4d3db892bee669f4b0319d1517283b295f7c306bcd
+size 964978368

model-00012-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01acce885605cc0b478d541dc762f75ee82f7970710467e223884ea7fe37e94
+size 964978368

model-00013-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d045d75e70d3ee216b594503714e2e529e312f5a81bef646b2738bbae27539ce
+size 998786192

model-00014-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:696b11c17882fe4195dcd9979dd1de5606b6b0224cfb44a358cd1973a67d1e34
+size 998778904

model-00015-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1864665859edc1bee43d4534d5fc9eb9da5f3fb82e9f42041308fa15060ad5
+size 964978376

model-00016-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1498aee7157bf888d63b725e4400fd8e3b0f366076097b570185775a673557b1
+size 964978392

model-00017-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0f2d3109ab3a6e4fee834cfdeece790c8ce3fa9abb64f2e97f5d6b39e67dfd3
+size 998786208

model-00018-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade78ed0f40ee7a6b2d22d0b4dadf2b338bcf25eb873fb1c51f1e70795595102
+size 998778920

model-00019-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d11b21844f1a594575e6ea19ba81845a3fdb1314ea40f0bf7ee66bb780a2ffe1
+size 964978392

model-00020-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:124614b6b4e7d3c8cfcc44aab35bfe63994c985e66604d83facc08bee15b5789
+size 964978392

model-00021-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d4b281f5445860f5bb01c7c32a7e73a228f188d617983f066215c3ea607437
+size 998786208

model-00022-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:984da3ec3e3e007b622aa8b35c5920caa85d37d9db4049ad1fed0c1d0d07b501
+size 998778920

model-00023-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:565f7bb32a0e4499decf1e533fef898d98d54af5ec4e924400da03be4a5fe5dd
+size 964978392

model-00024-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f3dda91065478cb33ec1dcd53fbe0d9d2960f9c6e3250257d97a84dc517baa
+size 964978392

model-00025-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abb5e895c7636c0bbcc02b4d62e5746d8dede0ec6e47456a33dc6755290bbb68
+size 998786208

model-00026-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:839941e4ca9a0b24e8aa447be24632806af0a085d14a86d8db54ea0d845a3717
+size 998778920

model-00027-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:232c046e8325fdb04e3c6926832aef2677be9a826d660fb0d8fee0fde63aa83f
+size 964978392

model-00028-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a3e55274d2dfff7f1d639afe565a4d94ca94eda157b70d0b5ae289087cdea8
+size 964978392

model-00029-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eda1d34c10f5f494c8d8d5383d837e9829faadd0ccdbda93c0e80a9f7f32829e
+size 998786208

model-00030-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dede43b482249ed4bee75e7aa05fd34bc8dd670b4b57980b08c2c2e36f3a299d
+size 998778920

model-00031-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec75237515411b9a1297c02ed8af5b369a6733269412f8b92197e559cddcc319
+size 964978392

model-00032-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0886813f79ef4785eb9e9cbb7ca89b9871d9b0f9db7cadd79b5a701c6ff07521
+size 964978392

model-00033-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13923104cce130bb1eaa3b9ed76e1c59919e5211000ed2180c6afbe3e0ece8bf
+size 998786208

model-00034-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b92f967f29ea33b94ef5f55b5f446b61589fa2e6c730fdf6a055fa760ab6729
+size 998778920

model-00035-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec47381cb96bba4a5b2c328d70207e09855ef048534a4cfcf283752c5311921c
+size 964978392

model-00036-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d5be1c8630b5538c13f764a87d8d0c96c3f7067766090a3e98ae3b23256198b
+size 964978392

model-00037-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fbdb11776c1be92f6147da4dc4a143a10bb2044174bb7e7d7a237c43e104453
+size 998786208

model-00038-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70148ce8f5bb453a32109ef87524db67e3c11ef3c9f44140b9e187104f2161a7
+size 998778920

model-00039-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c6cc7cbbc0428f0b9c527400d01f5967aa81c8e1eb26b5369987ea13dad191
+size 339763816

model-00040-of-00041.safetensors

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

model-00041-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7678f98dd1f390cc6a36dad66a2cd3702368ce69c019114de6dbe0a885cdce08
+size 1210192

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 38837980160}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00041.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00041.safetensors", "model.layers.0.mlp.experts.0.down_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.mlp.experts.1.down_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.mlp.experts.2.down_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.mlp.experts.3.down_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.mlp.experts.4.down_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.mlp.shared_expert.down_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.mlp.experts.2.gate_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.mlp.experts.3.gate_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.mlp.experts.4.gate_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.mlp.experts.0.up_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.mlp.experts.1.up_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.mlp.experts.2.up_proj.weight": "model-00003-of-00041.safetensors", "model.layers.0.mlp.experts.3.up_proj.weight": "model-00003-of-00041.safetensors", "model.layers.0.mlp.experts.4.up_proj.weight": "model-00003-of-00041.safetensors", "model.layers.0.mlp.shared_expert.up_proj.weight": "model-00003-of-00041.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00041.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00041.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00041.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00041.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00041.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00041.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00041.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00041.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00041.safetensors", "model.layers.1.mlp.experts.0.down_proj.weight": "model-00003-of-00041.safetensors", "model.layers.1.mlp.experts.1.down_proj.weight": "model-00003-of-00041.safetensors", "model.layers.1.mlp.experts.2.down_proj.weight": "model-00003-of-00041.safetensors", "model.layers.1.mlp.experts.3.down_proj.weight": "model-00003-of-00041.safetensors", "model.layers.1.mlp.experts.4.down_proj.weight": "model-00003-of-00041.safetensors", "model.layers.1.mlp.shared_expert.down_proj.weight": "model-00003-of-00041.safetensors", "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00003-of-00041.safetensors", "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00003-of-00041.safetensors", "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00003-of-00041.safetensors", "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00003-of-00041.safetensors", "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00004-of-00041.safetensors", "model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00004-of-00041.safetensors", "model.layers.1.mlp.experts.0.up_proj.weight": "model-00004-of-00041.safetensors", "model.layers.1.mlp.experts.1.up_proj.weight": "model-00004-of-00041.safetensors", "model.layers.1.mlp.experts.2.up_proj.weight": "model-00004-of-00041.safetensors", "model.layers.1.mlp.experts.3.up_proj.weight": "model-00004-of-00041.safetensors", "model.layers.1.mlp.experts.4.up_proj.weight": "model-00004-of-00041.safetensors", "model.layers.1.mlp.shared_expert.up_proj.weight": "model-00004-of-00041.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00041.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00004-of-00041.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00041.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00041.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00004-of-00041.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00041.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00004-of-00041.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00041.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00041.safetensors", "model.layers.2.mlp.experts.0.down_proj.weight": "model-00004-of-00041.safetensors", "model.layers.2.mlp.experts.1.down_proj.weight": "model-00004-of-00041.safetensors", "model.layers.2.mlp.experts.2.down_proj.weight": "model-00004-of-00041.safetensors", "model.layers.2.mlp.experts.3.down_proj.weight": "model-00004-of-00041.safetensors", "model.layers.2.mlp.experts.4.down_proj.weight": "model-00004-of-00041.safetensors", "model.layers.2.mlp.shared_expert.down_proj.weight": "model-00005-of-00041.safetensors", "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00005-of-00041.safetensors", "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00005-of-00041.safetensors", "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00005-of-00041.safetensors", "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00005-of-00041.safetensors", "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00005-of-00041.safetensors", "model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00005-of-00041.safetensors", "model.layers.2.mlp.experts.0.up_proj.weight": "model-00005-of-00041.safetensors", "model.layers.2.mlp.experts.1.up_proj.weight": "model-00005-of-00041.safetensors", "model.layers.2.mlp.experts.2.up_proj.weight": "model-00005-of-00041.safetensors", "model.layers.2.mlp.experts.3.up_proj.weight": "model-00005-of-00041.safetensors", "model.layers.2.mlp.experts.4.up_proj.weight": "model-00005-of-00041.safetensors", "model.layers.2.mlp.shared_expert.up_proj.weight": "model-00005-of-00041.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00041.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00005-of-00041.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00041.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00041.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00005-of-00041.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00041.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00006-of-00041.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00041.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00041.safetensors", "model.layers.3.mlp.experts.0.down_proj.weight": "model-00006-of-00041.safetensors", "model.layers.3.mlp.experts.1.down_proj.weight": "model-00006-of-00041.safetensors", "model.layers.3.mlp.experts.2.down_proj.weight": "model-00006-of-00041.safetensors", "model.layers.3.mlp.experts.3.down_proj.weight": "model-00006-of-00041.safetensors", "model.layers.3.mlp.experts.4.down_proj.weight": "model-00006-of-00041.safetensors", "model.layers.3.mlp.shared_expert.down_proj.weight": "model-00006-of-00041.safetensors", "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00006-of-00041.safetensors", "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00006-of-00041.safetensors", "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00006-of-00041.safetensors", "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00006-of-00041.safetensors", "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00006-of-00041.safetensors", "model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00006-of-00041.safetensors", "model.layers.3.mlp.experts.0.up_proj.weight": "model-00006-of-00041.safetensors", "model.layers.3.mlp.experts.1.up_proj.weight": "model-00007-of-00041.safetensors", "model.layers.3.mlp.experts.2.up_proj.weight": "model-00007-of-00041.safetensors", "model.layers.3.mlp.experts.3.up_proj.weight": "model-00007-of-00041.safetensors", "model.layers.3.mlp.experts.4.up_proj.weight": "model-00007-of-00041.safetensors", "model.layers.3.mlp.shared_expert.up_proj.weight": "model-00007-of-00041.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00041.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00007-of-00041.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00041.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00041.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00007-of-00041.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00041.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00007-of-00041.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00041.safetensors", "model.layers.4.input_layernorm.weight": "model-00007-of-00041.safetensors", "model.layers.4.mlp.experts.0.down_proj.weight": "model-00007-of-00041.safetensors", "model.layers.4.mlp.experts.1.down_proj.weight": "model-00007-of-00041.safetensors", "model.layers.4.mlp.experts.2.down_proj.weight": "model-00007-of-00041.safetensors", "model.layers.4.mlp.experts.3.down_proj.weight": "model-00007-of-00041.safetensors", "model.layers.4.mlp.experts.4.down_proj.weight": "model-00007-of-00041.safetensors", "model.layers.4.mlp.shared_expert.down_proj.weight": "model-00007-of-00041.safetensors", "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00007-of-00041.safetensors", "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00007-of-00041.safetensors", "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00007-of-00041.safetensors", "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00008-of-00041.safetensors", "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00008-of-00041.safetensors", "model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00008-of-00041.safetensors", "model.layers.4.mlp.experts.0.up_proj.weight": "model-00008-of-00041.safetensors", "model.layers.4.mlp.experts.1.up_proj.weight": "model-00008-of-00041.safetensors", "model.layers.4.mlp.experts.2.up_proj.weight": "model-00008-of-00041.safetensors", "model.layers.4.mlp.experts.3.up_proj.weight": "model-00008-of-00041.safetensors", "model.layers.4.mlp.experts.4.up_proj.weight": "model-00008-of-00041.safetensors", "model.layers.4.mlp.shared_expert.up_proj.weight": "model-00008-of-00041.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00041.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00008-of-00041.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00041.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00041.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00008-of-00041.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00041.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00008-of-00041.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00041.safetensors", "model.layers.5.input_layernorm.weight": "model-00008-of-00041.safetensors", "model.layers.5.mlp.experts.0.down_proj.weight": "model-00008-of-00041.safetensors", "model.layers.5.mlp.experts.1.down_proj.weight": "model-00008-of-00041.safetensors", "model.layers.5.mlp.experts.2.down_proj.weight": "model-00008-of-00041.safetensors", "model.layers.5.mlp.experts.3.down_proj.weight": "model-00008-of-00041.safetensors", "model.layers.5.mlp.experts.4.down_proj.weight": "model-00008-of-00041.safetensors", "model.layers.5.mlp.shared_expert.down_proj.weight": "model-00009-of-00041.safetensors", "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00009-of-00041.safetensors", "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00009-of-00041.safetensors", "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00009-of-00041.safetensors", "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00009-of-00041.safetensors", "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00009-of-00041.safetensors", "model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00009-of-00041.safetensors", "model.layers.5.mlp.experts.0.up_proj.weight": "model-00009-of-00041.safetensors", "model.layers.5.mlp.experts.1.up_proj.weight": "model-00009-of-00041.safetensors", "model.layers.5.mlp.experts.2.up_proj.weight": "model-00009-of-00041.safetensors", "model.layers.5.mlp.experts.3.up_proj.weight": "model-00009-of-00041.safetensors", "model.layers.5.mlp.experts.4.up_proj.weight": "model-00009-of-00041.safetensors", "model.layers.5.mlp.shared_expert.up_proj.weight": "model-00009-of-00041.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00041.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00009-of-00041.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00009-of-00041.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00009-of-00041.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00009-of-00041.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00041.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00010-of-00041.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00041.safetensors", "model.layers.6.input_layernorm.weight": "model-00010-of-00041.safetensors", "model.layers.6.mlp.experts.0.down_proj.weight": "model-00010-of-00041.safetensors", "model.layers.6.mlp.experts.1.down_proj.weight": "model-00010-of-00041.safetensors", "model.layers.6.mlp.experts.2.down_proj.weight": "model-00010-of-00041.safetensors", "model.layers.6.mlp.experts.3.down_proj.weight": "model-00010-of-00041.safetensors", "model.layers.6.mlp.experts.4.down_proj.weight": "model-00010-of-00041.safetensors", "model.layers.6.mlp.shared_expert.down_proj.weight": "model-00010-of-00041.safetensors", "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00010-of-00041.safetensors", "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00010-of-00041.safetensors", "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00010-of-00041.safetensors", "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00010-of-00041.safetensors", "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00010-of-00041.safetensors", "model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00010-of-00041.safetensors", "model.layers.6.mlp.experts.0.up_proj.weight": "model-00010-of-00041.safetensors", "model.layers.6.mlp.experts.1.up_proj.weight": "model-00011-of-00041.safetensors", "model.layers.6.mlp.experts.2.up_proj.weight": "model-00011-of-00041.safetensors", "model.layers.6.mlp.experts.3.up_proj.weight": "model-00011-of-00041.safetensors", "model.layers.6.mlp.experts.4.up_proj.weight": "model-00011-of-00041.safetensors", "model.layers.6.mlp.shared_expert.up_proj.weight": "model-00011-of-00041.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00011-of-00041.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00011-of-00041.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00011-of-00041.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00011-of-00041.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00011-of-00041.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00011-of-00041.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00011-of-00041.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00011-of-00041.safetensors", "model.layers.7.input_layernorm.weight": "model-00011-of-00041.safetensors", "model.layers.7.mlp.experts.0.down_proj.weight": "model-00011-of-00041.safetensors", "model.layers.7.mlp.experts.1.down_proj.weight": "model-00011-of-00041.safetensors", "model.layers.7.mlp.experts.2.down_proj.weight": "model-00011-of-00041.safetensors", "model.layers.7.mlp.experts.3.down_proj.weight": "model-00011-of-00041.safetensors", "model.layers.7.mlp.experts.4.down_proj.weight": "model-00011-of-00041.safetensors", "model.layers.7.mlp.shared_expert.down_proj.weight": "model-00011-of-00041.safetensors", "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00011-of-00041.safetensors", "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00011-of-00041.safetensors", "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00011-of-00041.safetensors", "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00012-of-00041.safetensors", "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00012-of-00041.safetensors", "model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00012-of-00041.safetensors", "model.layers.7.mlp.experts.0.up_proj.weight": "model-00012-of-00041.safetensors", "model.layers.7.mlp.experts.1.up_proj.weight": "model-00012-of-00041.safetensors", "model.layers.7.mlp.experts.2.up_proj.weight": "model-00012-of-00041.safetensors", "model.layers.7.mlp.experts.3.up_proj.weight": "model-00012-of-00041.safetensors", "model.layers.7.mlp.experts.4.up_proj.weight": "model-00012-of-00041.safetensors", "model.layers.7.mlp.shared_expert.up_proj.weight": "model-00012-of-00041.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00012-of-00041.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00012-of-00041.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00012-of-00041.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00012-of-00041.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00012-of-00041.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00012-of-00041.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00012-of-00041.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00012-of-00041.safetensors", "model.layers.8.input_layernorm.weight": "model-00012-of-00041.safetensors", "model.layers.8.mlp.experts.0.down_proj.weight": "model-00012-of-00041.safetensors", "model.layers.8.mlp.experts.1.down_proj.weight": "model-00012-of-00041.safetensors", "model.layers.8.mlp.experts.2.down_proj.weight": "model-00012-of-00041.safetensors", "model.layers.8.mlp.experts.3.down_proj.weight": "model-00012-of-00041.safetensors", "model.layers.8.mlp.experts.4.down_proj.weight": "model-00012-of-00041.safetensors", "model.layers.8.mlp.shared_expert.down_proj.weight": "model-00013-of-00041.safetensors", "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00013-of-00041.safetensors", "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00013-of-00041.safetensors", "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00013-of-00041.safetensors", "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00013-of-00041.safetensors", "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00013-of-00041.safetensors", "model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00013-of-00041.safetensors", "model.layers.8.mlp.experts.0.up_proj.weight": "model-00013-of-00041.safetensors", "model.layers.8.mlp.experts.1.up_proj.weight": "model-00013-of-00041.safetensors", "model.layers.8.mlp.experts.2.up_proj.weight": "model-00013-of-00041.safetensors", "model.layers.8.mlp.experts.3.up_proj.weight": "model-00013-of-00041.safetensors", "model.layers.8.mlp.experts.4.up_proj.weight": "model-00013-of-00041.safetensors", "model.layers.8.mlp.shared_expert.up_proj.weight": "model-00013-of-00041.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00013-of-00041.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00013-of-00041.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00013-of-00041.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00013-of-00041.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00013-of-00041.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00041.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00014-of-00041.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00041.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00041.safetensors", "model.layers.9.mlp.experts.0.down_proj.weight": "model-00014-of-00041.safetensors", "model.layers.9.mlp.experts.1.down_proj.weight": "model-00014-of-00041.safetensors", "model.layers.9.mlp.experts.2.down_proj.weight": "model-00014-of-00041.safetensors", "model.layers.9.mlp.experts.3.down_proj.weight": "model-00014-of-00041.safetensors", "model.layers.9.mlp.experts.4.down_proj.weight": "model-00014-of-00041.safetensors", "model.layers.9.mlp.shared_expert.down_proj.weight": "model-00014-of-00041.safetensors", "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00014-of-00041.safetensors", "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00014-of-00041.safetensors", "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00014-of-00041.safetensors", "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00014-of-00041.safetensors", "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00014-of-00041.safetensors", "model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00014-of-00041.safetensors", "model.layers.9.mlp.experts.0.up_proj.weight": "model-00014-of-00041.safetensors", "model.layers.9.mlp.experts.1.up_proj.weight": "model-00015-of-00041.safetensors", "model.layers.9.mlp.experts.2.up_proj.weight": "model-00015-of-00041.safetensors", "model.layers.9.mlp.experts.3.up_proj.weight": "model-00015-of-00041.safetensors", "model.layers.9.mlp.experts.4.up_proj.weight": "model-00015-of-00041.safetensors", "model.layers.9.mlp.shared_expert.up_proj.weight": "model-00015-of-00041.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00015-of-00041.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00015-of-00041.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00015-of-00041.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00015-of-00041.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00015-of-00041.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00015-of-00041.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00015-of-00041.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00015-of-00041.safetensors", "model.layers.10.input_layernorm.weight": "model-00015-of-00041.safetensors", "model.layers.10.mlp.experts.0.down_proj.weight": "model-00015-of-00041.safetensors", "model.layers.10.mlp.experts.1.down_proj.weight": "model-00015-of-00041.safetensors", "model.layers.10.mlp.experts.2.down_proj.weight": "model-00015-of-00041.safetensors", "model.layers.10.mlp.experts.3.down_proj.weight": "model-00015-of-00041.safetensors", "model.layers.10.mlp.experts.4.down_proj.weight": "model-00015-of-00041.safetensors", "model.layers.10.mlp.shared_expert.down_proj.weight": "model-00015-of-00041.safetensors", "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00015-of-00041.safetensors", "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00015-of-00041.safetensors", "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00015-of-00041.safetensors", "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00016-of-00041.safetensors", "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00016-of-00041.safetensors", "model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00016-of-00041.safetensors", "model.layers.10.mlp.experts.0.up_proj.weight": "model-00016-of-00041.safetensors", "model.layers.10.mlp.experts.1.up_proj.weight": "model-00016-of-00041.safetensors", "model.layers.10.mlp.experts.2.up_proj.weight": "model-00016-of-00041.safetensors", "model.layers.10.mlp.experts.3.up_proj.weight": "model-00016-of-00041.safetensors", "model.layers.10.mlp.experts.4.up_proj.weight": "model-00016-of-00041.safetensors", "model.layers.10.mlp.shared_expert.up_proj.weight": "model-00016-of-00041.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00016-of-00041.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00016-of-00041.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00016-of-00041.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00016-of-00041.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00016-of-00041.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00016-of-00041.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00016-of-00041.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00016-of-00041.safetensors", "model.layers.11.input_layernorm.weight": "model-00016-of-00041.safetensors", "model.layers.11.mlp.experts.0.down_proj.weight": "model-00016-of-00041.safetensors", "model.layers.11.mlp.experts.1.down_proj.weight": "model-00016-of-00041.safetensors", "model.layers.11.mlp.experts.2.down_proj.weight": "model-00016-of-00041.safetensors", "model.layers.11.mlp.experts.3.down_proj.weight": "model-00016-of-00041.safetensors", "model.layers.11.mlp.experts.4.down_proj.weight": "model-00016-of-00041.safetensors", "model.layers.11.mlp.shared_expert.down_proj.weight": "model-00017-of-00041.safetensors", "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00017-of-00041.safetensors", "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00017-of-00041.safetensors", "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00017-of-00041.safetensors", "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00017-of-00041.safetensors", "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00017-of-00041.safetensors", "model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00017-of-00041.safetensors", "model.layers.11.mlp.experts.0.up_proj.weight": "model-00017-of-00041.safetensors", "model.layers.11.mlp.experts.1.up_proj.weight": "model-00017-of-00041.safetensors", "model.layers.11.mlp.experts.2.up_proj.weight": "model-00017-of-00041.safetensors", "model.layers.11.mlp.experts.3.up_proj.weight": "model-00017-of-00041.safetensors", "model.layers.11.mlp.experts.4.up_proj.weight": "model-00017-of-00041.safetensors", "model.layers.11.mlp.shared_expert.up_proj.weight": "model-00017-of-00041.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00017-of-00041.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00017-of-00041.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00017-of-00041.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00017-of-00041.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00017-of-00041.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00018-of-00041.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00018-of-00041.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00018-of-00041.safetensors", "model.layers.12.input_layernorm.weight": "model-00018-of-00041.safetensors", "model.layers.12.mlp.experts.0.down_proj.weight": "model-00018-of-00041.safetensors", "model.layers.12.mlp.experts.1.down_proj.weight": "model-00018-of-00041.safetensors", "model.layers.12.mlp.experts.2.down_proj.weight": "model-00018-of-00041.safetensors", "model.layers.12.mlp.experts.3.down_proj.weight": "model-00018-of-00041.safetensors", "model.layers.12.mlp.experts.4.down_proj.weight": "model-00018-of-00041.safetensors", "model.layers.12.mlp.shared_expert.down_proj.weight": "model-00018-of-00041.safetensors", "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00018-of-00041.safetensors", "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00018-of-00041.safetensors", "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00018-of-00041.safetensors", "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00018-of-00041.safetensors", "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00018-of-00041.safetensors", "model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00018-of-00041.safetensors", "model.layers.12.mlp.experts.0.up_proj.weight": "model-00018-of-00041.safetensors", "model.layers.12.mlp.experts.1.up_proj.weight": "model-00019-of-00041.safetensors", "model.layers.12.mlp.experts.2.up_proj.weight": "model-00019-of-00041.safetensors", "model.layers.12.mlp.experts.3.up_proj.weight": "model-00019-of-00041.safetensors", "model.layers.12.mlp.experts.4.up_proj.weight": "model-00019-of-00041.safetensors", "model.layers.12.mlp.shared_expert.up_proj.weight": "model-00019-of-00041.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00019-of-00041.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00019-of-00041.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00019-of-00041.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00019-of-00041.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00019-of-00041.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00019-of-00041.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00019-of-00041.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00019-of-00041.safetensors", "model.layers.13.input_layernorm.weight": "model-00019-of-00041.safetensors", "model.layers.13.mlp.experts.0.down_proj.weight": "model-00019-of-00041.safetensors", "model.layers.13.mlp.experts.1.down_proj.weight": "model-00019-of-00041.safetensors", "model.layers.13.mlp.experts.2.down_proj.weight": "model-00019-of-00041.safetensors", "model.layers.13.mlp.experts.3.down_proj.weight": "model-00019-of-00041.safetensors", "model.layers.13.mlp.experts.4.down_proj.weight": "model-00019-of-00041.safetensors", "model.layers.13.mlp.shared_expert.down_proj.weight": "model-00019-of-00041.safetensors", "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00019-of-00041.safetensors", "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00019-of-00041.safetensors", "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00019-of-00041.safetensors", "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00020-of-00041.safetensors", "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00020-of-00041.safetensors", "model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00020-of-00041.safetensors", "model.layers.13.mlp.experts.0.up_proj.weight": "model-00020-of-00041.safetensors", "model.layers.13.mlp.experts.1.up_proj.weight": "model-00020-of-00041.safetensors", "model.layers.13.mlp.experts.2.up_proj.weight": "model-00020-of-00041.safetensors", "model.layers.13.mlp.experts.3.up_proj.weight": "model-00020-of-00041.safetensors", "model.layers.13.mlp.experts.4.up_proj.weight": "model-00020-of-00041.safetensors", "model.layers.13.mlp.shared_expert.up_proj.weight": "model-00020-of-00041.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00020-of-00041.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00020-of-00041.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00020-of-00041.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00020-of-00041.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00020-of-00041.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00020-of-00041.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00020-of-00041.safetensors", "model.layers.14.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.14.mlp.experts.0.down_proj.weight": "model-00020-of-00041.safetensors", "model.layers.14.mlp.experts.1.down_proj.weight": "model-00020-of-00041.safetensors", "model.layers.14.mlp.experts.2.down_proj.weight": "model-00020-of-00041.safetensors", "model.layers.14.mlp.experts.3.down_proj.weight": "model-00020-of-00041.safetensors", "model.layers.14.mlp.experts.4.down_proj.weight": "model-00020-of-00041.safetensors", "model.layers.14.mlp.shared_expert.down_proj.weight": "model-00021-of-00041.safetensors", "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00021-of-00041.safetensors", "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00021-of-00041.safetensors", "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00021-of-00041.safetensors", "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00021-of-00041.safetensors", "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00021-of-00041.safetensors", "model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00021-of-00041.safetensors", "model.layers.14.mlp.experts.0.up_proj.weight": "model-00021-of-00041.safetensors", "model.layers.14.mlp.experts.1.up_proj.weight": "model-00021-of-00041.safetensors", "model.layers.14.mlp.experts.2.up_proj.weight": "model-00021-of-00041.safetensors", "model.layers.14.mlp.experts.3.up_proj.weight": "model-00021-of-00041.safetensors", "model.layers.14.mlp.experts.4.up_proj.weight": "model-00021-of-00041.safetensors", "model.layers.14.mlp.shared_expert.up_proj.weight": "model-00021-of-00041.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00021-of-00041.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00021-of-00041.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00021-of-00041.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00021-of-00041.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00021-of-00041.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00022-of-00041.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00022-of-00041.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00022-of-00041.safetensors", "model.layers.15.input_layernorm.weight": "model-00022-of-00041.safetensors", "model.layers.15.mlp.experts.0.down_proj.weight": "model-00022-of-00041.safetensors", "model.layers.15.mlp.experts.1.down_proj.weight": "model-00022-of-00041.safetensors", "model.layers.15.mlp.experts.2.down_proj.weight": "model-00022-of-00041.safetensors", "model.layers.15.mlp.experts.3.down_proj.weight": "model-00022-of-00041.safetensors", "model.layers.15.mlp.experts.4.down_proj.weight": "model-00022-of-00041.safetensors", "model.layers.15.mlp.shared_expert.down_proj.weight": "model-00022-of-00041.safetensors", "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00022-of-00041.safetensors", "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00022-of-00041.safetensors", "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00022-of-00041.safetensors", "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00022-of-00041.safetensors", "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00022-of-00041.safetensors", "model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00022-of-00041.safetensors", "model.layers.15.mlp.experts.0.up_proj.weight": "model-00022-of-00041.safetensors", "model.layers.15.mlp.experts.1.up_proj.weight": "model-00023-of-00041.safetensors", "model.layers.15.mlp.experts.2.up_proj.weight": "model-00023-of-00041.safetensors", "model.layers.15.mlp.experts.3.up_proj.weight": "model-00023-of-00041.safetensors", "model.layers.15.mlp.experts.4.up_proj.weight": "model-00023-of-00041.safetensors", "model.layers.15.mlp.shared_expert.up_proj.weight": "model-00023-of-00041.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00023-of-00041.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00023-of-00041.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00023-of-00041.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00023-of-00041.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00023-of-00041.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00023-of-00041.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00023-of-00041.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00023-of-00041.safetensors", "model.layers.16.input_layernorm.weight": "model-00023-of-00041.safetensors", "model.layers.16.mlp.experts.0.down_proj.weight": "model-00023-of-00041.safetensors", "model.layers.16.mlp.experts.1.down_proj.weight": "model-00023-of-00041.safetensors", "model.layers.16.mlp.experts.2.down_proj.weight": "model-00023-of-00041.safetensors", "model.layers.16.mlp.experts.3.down_proj.weight": "model-00023-of-00041.safetensors", "model.layers.16.mlp.experts.4.down_proj.weight": "model-00023-of-00041.safetensors", "model.layers.16.mlp.shared_expert.down_proj.weight": "model-00023-of-00041.safetensors", "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00023-of-00041.safetensors", "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00023-of-00041.safetensors", "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00023-of-00041.safetensors", "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00024-of-00041.safetensors", "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00024-of-00041.safetensors", "model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00024-of-00041.safetensors", "model.layers.16.mlp.experts.0.up_proj.weight": "model-00024-of-00041.safetensors", "model.layers.16.mlp.experts.1.up_proj.weight": "model-00024-of-00041.safetensors", "model.layers.16.mlp.experts.2.up_proj.weight": "model-00024-of-00041.safetensors", "model.layers.16.mlp.experts.3.up_proj.weight": "model-00024-of-00041.safetensors", "model.layers.16.mlp.experts.4.up_proj.weight": "model-00024-of-00041.safetensors", "model.layers.16.mlp.shared_expert.up_proj.weight": "model-00024-of-00041.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00024-of-00041.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00024-of-00041.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00024-of-00041.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00024-of-00041.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00024-of-00041.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00024-of-00041.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00024-of-00041.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00024-of-00041.safetensors", "model.layers.17.input_layernorm.weight": "model-00024-of-00041.safetensors", "model.layers.17.mlp.experts.0.down_proj.weight": "model-00024-of-00041.safetensors", "model.layers.17.mlp.experts.1.down_proj.weight": "model-00024-of-00041.safetensors", "model.layers.17.mlp.experts.2.down_proj.weight": "model-00024-of-00041.safetensors", "model.layers.17.mlp.experts.3.down_proj.weight": "model-00024-of-00041.safetensors", "model.layers.17.mlp.experts.4.down_proj.weight": "model-00024-of-00041.safetensors", "model.layers.17.mlp.shared_expert.down_proj.weight": "model-00025-of-00041.safetensors", "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00025-of-00041.safetensors", "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00025-of-00041.safetensors", "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00025-of-00041.safetensors", "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00025-of-00041.safetensors", "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00025-of-00041.safetensors", "model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00025-of-00041.safetensors", "model.layers.17.mlp.experts.0.up_proj.weight": "model-00025-of-00041.safetensors", "model.layers.17.mlp.experts.1.up_proj.weight": "model-00025-of-00041.safetensors", "model.layers.17.mlp.experts.2.up_proj.weight": "model-00025-of-00041.safetensors", "model.layers.17.mlp.experts.3.up_proj.weight": "model-00025-of-00041.safetensors", "model.layers.17.mlp.experts.4.up_proj.weight": "model-00025-of-00041.safetensors", "model.layers.17.mlp.shared_expert.up_proj.weight": "model-00025-of-00041.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00025-of-00041.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00025-of-00041.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00025-of-00041.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00025-of-00041.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00025-of-00041.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00026-of-00041.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00026-of-00041.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00026-of-00041.safetensors", "model.layers.18.input_layernorm.weight": "model-00026-of-00041.safetensors", "model.layers.18.mlp.experts.0.down_proj.weight": "model-00026-of-00041.safetensors", "model.layers.18.mlp.experts.1.down_proj.weight": "model-00026-of-00041.safetensors", "model.layers.18.mlp.experts.2.down_proj.weight": "model-00026-of-00041.safetensors", "model.layers.18.mlp.experts.3.down_proj.weight": "model-00026-of-00041.safetensors", "model.layers.18.mlp.experts.4.down_proj.weight": "model-00026-of-00041.safetensors", "model.layers.18.mlp.shared_expert.down_proj.weight": "model-00026-of-00041.safetensors", "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00026-of-00041.safetensors", "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00026-of-00041.safetensors", "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00026-of-00041.safetensors", "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00026-of-00041.safetensors", "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00026-of-00041.safetensors", "model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00026-of-00041.safetensors", "model.layers.18.mlp.experts.0.up_proj.weight": "model-00026-of-00041.safetensors", "model.layers.18.mlp.experts.1.up_proj.weight": "model-00027-of-00041.safetensors", "model.layers.18.mlp.experts.2.up_proj.weight": "model-00027-of-00041.safetensors", "model.layers.18.mlp.experts.3.up_proj.weight": "model-00027-of-00041.safetensors", "model.layers.18.mlp.experts.4.up_proj.weight": "model-00027-of-00041.safetensors", "model.layers.18.mlp.shared_expert.up_proj.weight": "model-00027-of-00041.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00027-of-00041.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00027-of-00041.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00027-of-00041.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00027-of-00041.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00027-of-00041.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00027-of-00041.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00027-of-00041.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00027-of-00041.safetensors", "model.layers.19.input_layernorm.weight": "model-00027-of-00041.safetensors", "model.layers.19.mlp.experts.0.down_proj.weight": "model-00027-of-00041.safetensors", "model.layers.19.mlp.experts.1.down_proj.weight": "model-00027-of-00041.safetensors", "model.layers.19.mlp.experts.2.down_proj.weight": "model-00027-of-00041.safetensors", "model.layers.19.mlp.experts.3.down_proj.weight": "model-00027-of-00041.safetensors", "model.layers.19.mlp.experts.4.down_proj.weight": "model-00027-of-00041.safetensors", "model.layers.19.mlp.shared_expert.down_proj.weight": "model-00027-of-00041.safetensors", "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00027-of-00041.safetensors", "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00027-of-00041.safetensors", "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00027-of-00041.safetensors", "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00028-of-00041.safetensors", "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00028-of-00041.safetensors", "model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00028-of-00041.safetensors", "model.layers.19.mlp.experts.0.up_proj.weight": "model-00028-of-00041.safetensors", "model.layers.19.mlp.experts.1.up_proj.weight": "model-00028-of-00041.safetensors", "model.layers.19.mlp.experts.2.up_proj.weight": "model-00028-of-00041.safetensors", "model.layers.19.mlp.experts.3.up_proj.weight": "model-00028-of-00041.safetensors", "model.layers.19.mlp.experts.4.up_proj.weight": "model-00028-of-00041.safetensors", "model.layers.19.mlp.shared_expert.up_proj.weight": "model-00028-of-00041.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00028-of-00041.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00028-of-00041.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00028-of-00041.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00028-of-00041.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00028-of-00041.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00028-of-00041.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00028-of-00041.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00028-of-00041.safetensors", "model.layers.20.input_layernorm.weight": "model-00028-of-00041.safetensors", "model.layers.20.mlp.experts.0.down_proj.weight": "model-00028-of-00041.safetensors", "model.layers.20.mlp.experts.1.down_proj.weight": "model-00028-of-00041.safetensors", "model.layers.20.mlp.experts.2.down_proj.weight": "model-00028-of-00041.safetensors", "model.layers.20.mlp.experts.3.down_proj.weight": "model-00028-of-00041.safetensors", "model.layers.20.mlp.experts.4.down_proj.weight": "model-00028-of-00041.safetensors", "model.layers.20.mlp.shared_expert.down_proj.weight": "model-00029-of-00041.safetensors", "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00029-of-00041.safetensors", "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00029-of-00041.safetensors", "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00029-of-00041.safetensors", "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00029-of-00041.safetensors", "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00029-of-00041.safetensors", "model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00029-of-00041.safetensors", "model.layers.20.mlp.experts.0.up_proj.weight": "model-00029-of-00041.safetensors", "model.layers.20.mlp.experts.1.up_proj.weight": "model-00029-of-00041.safetensors", "model.layers.20.mlp.experts.2.up_proj.weight": "model-00029-of-00041.safetensors", "model.layers.20.mlp.experts.3.up_proj.weight": "model-00029-of-00041.safetensors", "model.layers.20.mlp.experts.4.up_proj.weight": "model-00029-of-00041.safetensors", "model.layers.20.mlp.shared_expert.up_proj.weight": "model-00029-of-00041.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00029-of-00041.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00029-of-00041.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00029-of-00041.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00029-of-00041.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00029-of-00041.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00030-of-00041.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00030-of-00041.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00030-of-00041.safetensors", "model.layers.21.input_layernorm.weight": "model-00030-of-00041.safetensors", "model.layers.21.mlp.experts.0.down_proj.weight": "model-00030-of-00041.safetensors", "model.layers.21.mlp.experts.1.down_proj.weight": "model-00030-of-00041.safetensors", "model.layers.21.mlp.experts.2.down_proj.weight": "model-00030-of-00041.safetensors", "model.layers.21.mlp.experts.3.down_proj.weight": "model-00030-of-00041.safetensors", "model.layers.21.mlp.experts.4.down_proj.weight": "model-00030-of-00041.safetensors", "model.layers.21.mlp.shared_expert.down_proj.weight": "model-00030-of-00041.safetensors", "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00030-of-00041.safetensors", "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00030-of-00041.safetensors", "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00030-of-00041.safetensors", "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00030-of-00041.safetensors", "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00030-of-00041.safetensors", "model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00030-of-00041.safetensors", "model.layers.21.mlp.experts.0.up_proj.weight": "model-00030-of-00041.safetensors", "model.layers.21.mlp.experts.1.up_proj.weight": "model-00031-of-00041.safetensors", "model.layers.21.mlp.experts.2.up_proj.weight": "model-00031-of-00041.safetensors", "model.layers.21.mlp.experts.3.up_proj.weight": "model-00031-of-00041.safetensors", "model.layers.21.mlp.experts.4.up_proj.weight": "model-00031-of-00041.safetensors", "model.layers.21.mlp.shared_expert.up_proj.weight": "model-00031-of-00041.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00031-of-00041.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00031-of-00041.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00031-of-00041.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00031-of-00041.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00031-of-00041.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00031-of-00041.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00031-of-00041.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00031-of-00041.safetensors", "model.layers.22.input_layernorm.weight": "model-00031-of-00041.safetensors", "model.layers.22.mlp.experts.0.down_proj.weight": "model-00031-of-00041.safetensors", "model.layers.22.mlp.experts.1.down_proj.weight": "model-00031-of-00041.safetensors", "model.layers.22.mlp.experts.2.down_proj.weight": "model-00031-of-00041.safetensors", "model.layers.22.mlp.experts.3.down_proj.weight": "model-00031-of-00041.safetensors", "model.layers.22.mlp.experts.4.down_proj.weight": "model-00031-of-00041.safetensors", "model.layers.22.mlp.shared_expert.down_proj.weight": "model-00031-of-00041.safetensors", "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00031-of-00041.safetensors", "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00031-of-00041.safetensors", "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00031-of-00041.safetensors", "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00032-of-00041.safetensors", "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00032-of-00041.safetensors", "model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00032-of-00041.safetensors", "model.layers.22.mlp.experts.0.up_proj.weight": "model-00032-of-00041.safetensors", "model.layers.22.mlp.experts.1.up_proj.weight": "model-00032-of-00041.safetensors", "model.layers.22.mlp.experts.2.up_proj.weight": "model-00032-of-00041.safetensors", "model.layers.22.mlp.experts.3.up_proj.weight": "model-00032-of-00041.safetensors", "model.layers.22.mlp.experts.4.up_proj.weight": "model-00032-of-00041.safetensors", "model.layers.22.mlp.shared_expert.up_proj.weight": "model-00032-of-00041.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00032-of-00041.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00032-of-00041.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00032-of-00041.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00032-of-00041.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00032-of-00041.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00032-of-00041.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00032-of-00041.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00032-of-00041.safetensors", "model.layers.23.input_layernorm.weight": "model-00032-of-00041.safetensors", "model.layers.23.mlp.experts.0.down_proj.weight": "model-00032-of-00041.safetensors", "model.layers.23.mlp.experts.1.down_proj.weight": "model-00032-of-00041.safetensors", "model.layers.23.mlp.experts.2.down_proj.weight": "model-00032-of-00041.safetensors", "model.layers.23.mlp.experts.3.down_proj.weight": "model-00032-of-00041.safetensors", "model.layers.23.mlp.experts.4.down_proj.weight": "model-00032-of-00041.safetensors", "model.layers.23.mlp.shared_expert.down_proj.weight": "model-00033-of-00041.safetensors", "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00033-of-00041.safetensors", "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00033-of-00041.safetensors", "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00033-of-00041.safetensors", "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00033-of-00041.safetensors", "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00033-of-00041.safetensors", "model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00033-of-00041.safetensors", "model.layers.23.mlp.experts.0.up_proj.weight": "model-00033-of-00041.safetensors", "model.layers.23.mlp.experts.1.up_proj.weight": "model-00033-of-00041.safetensors", "model.layers.23.mlp.experts.2.up_proj.weight": "model-00033-of-00041.safetensors", "model.layers.23.mlp.experts.3.up_proj.weight": "model-00033-of-00041.safetensors", "model.layers.23.mlp.experts.4.up_proj.weight": "model-00033-of-00041.safetensors", "model.layers.23.mlp.shared_expert.up_proj.weight": "model-00033-of-00041.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00033-of-00041.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00033-of-00041.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00033-of-00041.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00033-of-00041.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00033-of-00041.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00034-of-00041.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00034-of-00041.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00034-of-00041.safetensors", "model.layers.24.input_layernorm.weight": "model-00034-of-00041.safetensors", "model.layers.24.mlp.experts.0.down_proj.weight": "model-00034-of-00041.safetensors", "model.layers.24.mlp.experts.1.down_proj.weight": "model-00034-of-00041.safetensors", "model.layers.24.mlp.experts.2.down_proj.weight": "model-00034-of-00041.safetensors", "model.layers.24.mlp.experts.3.down_proj.weight": "model-00034-of-00041.safetensors", "model.layers.24.mlp.experts.4.down_proj.weight": "model-00034-of-00041.safetensors", "model.layers.24.mlp.shared_expert.down_proj.weight": "model-00034-of-00041.safetensors", "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00034-of-00041.safetensors", "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00034-of-00041.safetensors", "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00034-of-00041.safetensors", "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00034-of-00041.safetensors", "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00034-of-00041.safetensors", "model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00034-of-00041.safetensors", "model.layers.24.mlp.experts.0.up_proj.weight": "model-00034-of-00041.safetensors", "model.layers.24.mlp.experts.1.up_proj.weight": "model-00035-of-00041.safetensors", "model.layers.24.mlp.experts.2.up_proj.weight": "model-00035-of-00041.safetensors", "model.layers.24.mlp.experts.3.up_proj.weight": "model-00035-of-00041.safetensors", "model.layers.24.mlp.experts.4.up_proj.weight": "model-00035-of-00041.safetensors", "model.layers.24.mlp.shared_expert.up_proj.weight": "model-00035-of-00041.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00035-of-00041.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00035-of-00041.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00035-of-00041.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00035-of-00041.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00035-of-00041.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00035-of-00041.safetensors", "model.layers.25.input_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.25.mlp.experts.0.down_proj.weight": "model-00035-of-00041.safetensors", "model.layers.25.mlp.experts.1.down_proj.weight": "model-00035-of-00041.safetensors", "model.layers.25.mlp.experts.2.down_proj.weight": "model-00035-of-00041.safetensors", "model.layers.25.mlp.experts.3.down_proj.weight": "model-00035-of-00041.safetensors", "model.layers.25.mlp.experts.4.down_proj.weight": "model-00035-of-00041.safetensors", "model.layers.25.mlp.shared_expert.down_proj.weight": "model-00035-of-00041.safetensors", "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00035-of-00041.safetensors", "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00035-of-00041.safetensors", "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00035-of-00041.safetensors", "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00036-of-00041.safetensors", "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00036-of-00041.safetensors", "model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00036-of-00041.safetensors", "model.layers.25.mlp.experts.0.up_proj.weight": "model-00036-of-00041.safetensors", "model.layers.25.mlp.experts.1.up_proj.weight": "model-00036-of-00041.safetensors", "model.layers.25.mlp.experts.2.up_proj.weight": "model-00036-of-00041.safetensors", "model.layers.25.mlp.experts.3.up_proj.weight": "model-00036-of-00041.safetensors", "model.layers.25.mlp.experts.4.up_proj.weight": "model-00036-of-00041.safetensors", "model.layers.25.mlp.shared_expert.up_proj.weight": "model-00036-of-00041.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00036-of-00041.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00036-of-00041.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00036-of-00041.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00036-of-00041.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00036-of-00041.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00036-of-00041.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00036-of-00041.safetensors", "model.layers.26.input_layernorm.weight": "model-00036-of-00041.safetensors", "model.layers.26.mlp.experts.0.down_proj.weight": "model-00036-of-00041.safetensors", "model.layers.26.mlp.experts.1.down_proj.weight": "model-00036-of-00041.safetensors", "model.layers.26.mlp.experts.2.down_proj.weight": "model-00036-of-00041.safetensors", "model.layers.26.mlp.experts.3.down_proj.weight": "model-00036-of-00041.safetensors", "model.layers.26.mlp.experts.4.down_proj.weight": "model-00036-of-00041.safetensors", "model.layers.26.mlp.shared_expert.down_proj.weight": "model-00037-of-00041.safetensors", "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00037-of-00041.safetensors", "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00037-of-00041.safetensors", "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00037-of-00041.safetensors", "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00037-of-00041.safetensors", "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00037-of-00041.safetensors", "model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00037-of-00041.safetensors", "model.layers.26.mlp.experts.0.up_proj.weight": "model-00037-of-00041.safetensors", "model.layers.26.mlp.experts.1.up_proj.weight": "model-00037-of-00041.safetensors", "model.layers.26.mlp.experts.2.up_proj.weight": "model-00037-of-00041.safetensors", "model.layers.26.mlp.experts.3.up_proj.weight": "model-00037-of-00041.safetensors", "model.layers.26.mlp.experts.4.up_proj.weight": "model-00037-of-00041.safetensors", "model.layers.26.mlp.shared_expert.up_proj.weight": "model-00037-of-00041.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00037-of-00041.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00037-of-00041.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00037-of-00041.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00037-of-00041.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00037-of-00041.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00038-of-00041.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.27.input_layernorm.weight": "model-00038-of-00041.safetensors", "model.layers.27.mlp.experts.0.down_proj.weight": "model-00038-of-00041.safetensors", "model.layers.27.mlp.experts.1.down_proj.weight": "model-00038-of-00041.safetensors", "model.layers.27.mlp.experts.2.down_proj.weight": "model-00038-of-00041.safetensors", "model.layers.27.mlp.experts.3.down_proj.weight": "model-00038-of-00041.safetensors", "model.layers.27.mlp.experts.4.down_proj.weight": "model-00038-of-00041.safetensors", "model.layers.27.mlp.shared_expert.down_proj.weight": "model-00038-of-00041.safetensors", "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00038-of-00041.safetensors", "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00038-of-00041.safetensors", "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00038-of-00041.safetensors", "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00038-of-00041.safetensors", "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00038-of-00041.safetensors", "model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00038-of-00041.safetensors", "model.layers.27.mlp.experts.0.up_proj.weight": "model-00038-of-00041.safetensors", "model.layers.27.mlp.experts.1.up_proj.weight": "model-00039-of-00041.safetensors", "model.layers.27.mlp.experts.2.up_proj.weight": "model-00039-of-00041.safetensors", "model.layers.27.mlp.experts.3.up_proj.weight": "model-00039-of-00041.safetensors", "model.layers.27.mlp.experts.4.up_proj.weight": "model-00039-of-00041.safetensors", "model.layers.27.mlp.shared_expert.up_proj.weight": "model-00039-of-00041.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00039-of-00041.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00039-of-00041.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00039-of-00041.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00039-of-00041.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00039-of-00041.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00039-of-00041.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00039-of-00041.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00039-of-00041.safetensors", "model.norm.weight": "model-00039-of-00041.safetensors", "lm_head.weight": "model-00040-of-00041.safetensors", "model.layers.0.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.0.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.1.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.1.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.2.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.2.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.3.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.3.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.4.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.4.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.5.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.5.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.6.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.6.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.7.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.7.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.8.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.8.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.9.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.9.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.10.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.10.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.11.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.11.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.12.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.12.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.13.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.13.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.14.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.14.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.15.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.15.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.16.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.16.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.17.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.17.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.18.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.18.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.19.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.19.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.20.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.20.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.21.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.21.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.22.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.22.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.23.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.23.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.24.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.24.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.25.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.25.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.26.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.26.mlp.shared_expert_gate.weight": "model-00041-of-00041.safetensors", "model.layers.27.mlp.gate.weight": "model-00041-of-00041.safetensors", "model.layers.27.mlp.shared_expert_gate.weight": "model-00041-of-00041.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 +1,208 @@
+{
+  "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": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}