upload model folder to repo

.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
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "/aifs4su/yaodong/spring_r1/boyuan_eval/outputs/hardcode_pku_third_hospital_preview/slice_end",
+  "architectures": [
+    "Qwen2VLModel"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 80,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 8192,
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14,
+    "torch_dtype": "bfloat16"
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

model-00001-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cff9be75406f04f7f3f879a789c916ab96d2da7dbb27672eeb332000a5987a5
+size 4548798608

model-00002-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3faefdd144966bf1daa2ccc69695c0d259864552c4d266625840e220d60592
+size 4964101216

model-00003-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a0ae3044aa40f908a10ccced36694cdadd797dfcca6b73d307e04b410bfc82
+size 4781637128

model-00004-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef23a7d69a5deba7e7d5ac8958f71abccd3e2306836c3be420d828fc9e1ebf98
+size 4781670112

model-00005-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096a67bee5ffdf917e380f898cea534ce5970e8783c708df45b76f16a4a95a9c
+size 4781670144

model-00006-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaebe844b53bb3765b91462626f7f0abce7affcc3f30eff8dd7dc2adbf77ef0a
+size 4964101240

model-00007-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4423d9e286e2aa447311b3f5a3152e982f6ea7ffb82a83e12a125ad5a9a74b5f
+size 4781637160

model-00008-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b0d77da7e83013d38cfa64041e3caf302afa01e24b10eb8cff5cd38d45c966
+size 4781670152

model-00009-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e1223bf11dcaa4e93bc16ad331a384fde539e156d6136260943af78582c82f
+size 4781670144

model-00010-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a6eda4696bd9001c5cc81bf4c4a61238388e8851d83505e393684f0723204b
+size 4964101240

model-00011-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23c99b54f76ef0c55f3dcd0dd38be8caa0dd6af8ae547a0300700d0839d92c78
+size 4781637160

model-00012-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c427f21c93bce9020d10f3b5e69481cf8d894fc071eea10c169de793f23417f
+size 4781670152

model-00013-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b78c3d9abecf5e5c2ecf2f6ad83bf558946bc279967eac916474f66b68a3d6
+size 4781670144

model-00014-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce04399dc6aa0f452bc593900e2403b539f3edfae09693b76862bdc5df5c904
+size 4964101240

model-00015-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bb33e01fb26335d3e276c36d615bde2b7e5c9b7e14ed447815c468a7183b1ef
+size 4781637160

model-00016-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa2e69c6140f5451203bb3e3a6e02464ac424ba928f0eb27c05643b17982964
+size 4781670152

model-00017-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8abb90ce4585fbb3b66549350c7a479f044b081a2024db7aaf410659e07ace7e
+size 4781670144

model-00018-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc51004a7c925e9ffbb99a34c1f5a2ca2adf5ce96301501f3e436ee98056c644
+size 4964101240

model-00019-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff1ff5bac504027db48b4681b8096fdefd4c97e6625ba1b12dcce51b5a2f9dbe
+size 4781637160

model-00020-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d03f5c6257daea84ed8767731103275d992c4e615fda294c3957d24e688251c6
+size 4781670152

model-00021-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3d742a264dc84ef8a76ea8db1f6007905d212e388bb3cde6845e5eada9bd2c5
+size 4781670144

model-00022-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c78cb631372fefa83d7ef5ceb169175d0eb3870d998507818eaebc480eb1ba2
+size 4964101240

model-00023-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0773b932fabc9ed06da975298a33d3d0d22d9d567940eab6fff5c634dbde56ef
+size 4781637160

model-00024-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03efa87972f68d0cce1f58978fdf1e6b51ca7c18f58f7e5bc6e6d9e8883167e5
+size 4781670152

model-00025-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac94974aeef44ef01da88185ce38fc04a056c93b96fbddcd1d7ab228fb64825
+size 4781670144

model-00026-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11393cf6d72a06ab03243314cee26498cdf74c644fb9e51d7abc4669bed1dd8f
+size 4964101240

model-00027-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa399f624876fb40067871169edbb62c9705c06070d2fc75c4a2cf06f9fbd308
+size 4781637160

model-00028-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5892307569151f6416b2a909d4cf6e4e2383b90fcf1c3cd37ca2a6c68e990d
+size 4781670152

model-00029-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:504d89350e64c269e1d0489a3a2661047dc39e99c3af7483daff313b55be9461
+size 4781670144

model-00030-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6d9934b86df1f3fa9007ec95a20b664d5616e5a9648f9ef0db2cad4cf541498
+size 3208746928

model.safetensors.index.json

@@ -0,0 +1,969 @@
+{
+  "metadata": {
+    "total_size": 142920990720
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00030.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00030.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00030.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00030.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
+    "layers.0.self_attn.k_proj.bias": "model-00001-of-00030.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
+    "layers.0.self_attn.q_proj.bias": "model-00001-of-00030.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
+    "layers.0.self_attn.v_proj.bias": "model-00001-of-00030.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
+    "layers.1.input_layernorm.weight": "model-00002-of-00030.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
+    "layers.1.self_attn.k_proj.bias": "model-00001-of-00030.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
+    "layers.1.self_attn.q_proj.bias": "model-00001-of-00030.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
+    "layers.1.self_attn.v_proj.bias": "model-00001-of-00030.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
+    "layers.10.input_layernorm.weight": "model-00005-of-00030.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
+    "layers.10.self_attn.k_proj.bias": "model-00005-of-00030.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.10.self_attn.q_proj.bias": "model-00005-of-00030.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.10.self_attn.v_proj.bias": "model-00005-of-00030.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.11.input_layernorm.weight": "model-00005-of-00030.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
+    "layers.11.self_attn.k_proj.bias": "model-00005-of-00030.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.11.self_attn.q_proj.bias": "model-00005-of-00030.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.11.self_attn.v_proj.bias": "model-00005-of-00030.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.12.input_layernorm.weight": "model-00006-of-00030.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
+    "layers.12.self_attn.k_proj.bias": "model-00005-of-00030.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.12.self_attn.q_proj.bias": "model-00005-of-00030.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.12.self_attn.v_proj.bias": "model-00005-of-00030.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.13.input_layernorm.weight": "model-00006-of-00030.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
+    "layers.13.self_attn.k_proj.bias": "model-00006-of-00030.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.13.self_attn.q_proj.bias": "model-00006-of-00030.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.13.self_attn.v_proj.bias": "model-00006-of-00030.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.14.input_layernorm.weight": "model-00006-of-00030.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
+    "layers.14.self_attn.k_proj.bias": "model-00006-of-00030.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.14.self_attn.q_proj.bias": "model-00006-of-00030.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.14.self_attn.v_proj.bias": "model-00006-of-00030.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
+    "layers.15.input_layernorm.weight": "model-00007-of-00030.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
+    "layers.15.self_attn.k_proj.bias": "model-00007-of-00030.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.15.self_attn.q_proj.bias": "model-00007-of-00030.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.15.self_attn.v_proj.bias": "model-00007-of-00030.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.16.input_layernorm.weight": "model-00007-of-00030.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
+    "layers.16.self_attn.k_proj.bias": "model-00007-of-00030.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.16.self_attn.q_proj.bias": "model-00007-of-00030.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.16.self_attn.v_proj.bias": "model-00007-of-00030.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.17.input_layernorm.weight": "model-00008-of-00030.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
+    "layers.17.self_attn.k_proj.bias": "model-00007-of-00030.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.17.self_attn.q_proj.bias": "model-00007-of-00030.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.17.self_attn.v_proj.bias": "model-00007-of-00030.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
+    "layers.18.input_layernorm.weight": "model-00008-of-00030.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
+    "layers.18.self_attn.k_proj.bias": "model-00008-of-00030.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.18.self_attn.q_proj.bias": "model-00008-of-00030.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.18.self_attn.v_proj.bias": "model-00008-of-00030.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.19.input_layernorm.weight": "model-00008-of-00030.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
+    "layers.19.self_attn.k_proj.bias": "model-00008-of-00030.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.19.self_attn.q_proj.bias": "model-00008-of-00030.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.19.self_attn.v_proj.bias": "model-00008-of-00030.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.2.input_layernorm.weight": "model-00002-of-00030.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
+    "layers.2.self_attn.k_proj.bias": "model-00002-of-00030.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.2.self_attn.q_proj.bias": "model-00002-of-00030.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.2.self_attn.v_proj.bias": "model-00002-of-00030.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.20.input_layernorm.weight": "model-00009-of-00030.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
+    "layers.20.self_attn.k_proj.bias": "model-00008-of-00030.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.20.self_attn.q_proj.bias": "model-00008-of-00030.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.20.self_attn.v_proj.bias": "model-00008-of-00030.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
+    "layers.21.input_layernorm.weight": "model-00009-of-00030.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
+    "layers.21.self_attn.k_proj.bias": "model-00009-of-00030.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.21.self_attn.q_proj.bias": "model-00009-of-00030.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.21.self_attn.v_proj.bias": "model-00009-of-00030.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.22.input_layernorm.weight": "model-00009-of-00030.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
+    "layers.22.self_attn.k_proj.bias": "model-00009-of-00030.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.22.self_attn.q_proj.bias": "model-00009-of-00030.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.22.self_attn.v_proj.bias": "model-00009-of-00030.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.23.input_layernorm.weight": "model-00010-of-00030.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
+    "layers.23.self_attn.k_proj.bias": "model-00009-of-00030.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.23.self_attn.q_proj.bias": "model-00009-of-00030.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.23.self_attn.v_proj.bias": "model-00009-of-00030.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
+    "layers.24.input_layernorm.weight": "model-00010-of-00030.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
+    "layers.24.self_attn.k_proj.bias": "model-00010-of-00030.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.24.self_attn.q_proj.bias": "model-00010-of-00030.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.24.self_attn.v_proj.bias": "model-00010-of-00030.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.25.input_layernorm.weight": "model-00010-of-00030.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
+    "layers.25.self_attn.k_proj.bias": "model-00010-of-00030.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.25.self_attn.q_proj.bias": "model-00010-of-00030.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.25.self_attn.v_proj.bias": "model-00010-of-00030.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
+    "layers.26.input_layernorm.weight": "model-00011-of-00030.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
+    "layers.26.self_attn.k_proj.bias": "model-00011-of-00030.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.26.self_attn.q_proj.bias": "model-00011-of-00030.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.26.self_attn.v_proj.bias": "model-00011-of-00030.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.27.input_layernorm.weight": "model-00011-of-00030.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
+    "layers.27.self_attn.k_proj.bias": "model-00011-of-00030.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.27.self_attn.q_proj.bias": "model-00011-of-00030.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.27.self_attn.v_proj.bias": "model-00011-of-00030.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.28.input_layernorm.weight": "model-00012-of-00030.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
+    "layers.28.self_attn.k_proj.bias": "model-00011-of-00030.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.28.self_attn.q_proj.bias": "model-00011-of-00030.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.28.self_attn.v_proj.bias": "model-00011-of-00030.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
+    "layers.29.input_layernorm.weight": "model-00012-of-00030.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
+    "layers.29.self_attn.k_proj.bias": "model-00012-of-00030.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.29.self_attn.q_proj.bias": "model-00012-of-00030.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.29.self_attn.v_proj.bias": "model-00012-of-00030.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.3.input_layernorm.weight": "model-00002-of-00030.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
+    "layers.3.self_attn.k_proj.bias": "model-00002-of-00030.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.3.self_attn.q_proj.bias": "model-00002-of-00030.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.3.self_attn.v_proj.bias": "model-00002-of-00030.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
+    "layers.30.input_layernorm.weight": "model-00012-of-00030.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
+    "layers.30.self_attn.k_proj.bias": "model-00012-of-00030.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.30.self_attn.q_proj.bias": "model-00012-of-00030.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.30.self_attn.v_proj.bias": "model-00012-of-00030.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.31.input_layernorm.weight": "model-00013-of-00030.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
+    "layers.31.self_attn.k_proj.bias": "model-00012-of-00030.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.31.self_attn.q_proj.bias": "model-00012-of-00030.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.31.self_attn.v_proj.bias": "model-00012-of-00030.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
+    "layers.32.input_layernorm.weight": "model-00013-of-00030.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.32.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.32.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
+    "layers.32.self_attn.k_proj.bias": "model-00013-of-00030.safetensors",
+    "layers.32.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.32.self_attn.q_proj.bias": "model-00013-of-00030.safetensors",
+    "layers.32.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.32.self_attn.v_proj.bias": "model-00013-of-00030.safetensors",
+    "layers.32.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.33.input_layernorm.weight": "model-00013-of-00030.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.33.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.33.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
+    "layers.33.self_attn.k_proj.bias": "model-00013-of-00030.safetensors",
+    "layers.33.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.33.self_attn.q_proj.bias": "model-00013-of-00030.safetensors",
+    "layers.33.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.33.self_attn.v_proj.bias": "model-00013-of-00030.safetensors",
+    "layers.33.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.34.input_layernorm.weight": "model-00014-of-00030.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.34.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.34.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
+    "layers.34.self_attn.k_proj.bias": "model-00013-of-00030.safetensors",
+    "layers.34.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.34.self_attn.q_proj.bias": "model-00013-of-00030.safetensors",
+    "layers.34.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.34.self_attn.v_proj.bias": "model-00013-of-00030.safetensors",
+    "layers.34.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
+    "layers.35.input_layernorm.weight": "model-00014-of-00030.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.35.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.35.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
+    "layers.35.self_attn.k_proj.bias": "model-00014-of-00030.safetensors",
+    "layers.35.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.35.self_attn.q_proj.bias": "model-00014-of-00030.safetensors",
+    "layers.35.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.35.self_attn.v_proj.bias": "model-00014-of-00030.safetensors",
+    "layers.35.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.36.input_layernorm.weight": "model-00014-of-00030.safetensors",
+    "layers.36.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.36.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.36.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.36.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
+    "layers.36.self_attn.k_proj.bias": "model-00014-of-00030.safetensors",
+    "layers.36.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.36.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.36.self_attn.q_proj.bias": "model-00014-of-00030.safetensors",
+    "layers.36.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.36.self_attn.v_proj.bias": "model-00014-of-00030.safetensors",
+    "layers.36.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
+    "layers.37.input_layernorm.weight": "model-00015-of-00030.safetensors",
+    "layers.37.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.37.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.37.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.37.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
+    "layers.37.self_attn.k_proj.bias": "model-00015-of-00030.safetensors",
+    "layers.37.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.37.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.37.self_attn.q_proj.bias": "model-00015-of-00030.safetensors",
+    "layers.37.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.37.self_attn.v_proj.bias": "model-00015-of-00030.safetensors",
+    "layers.37.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.38.input_layernorm.weight": "model-00015-of-00030.safetensors",
+    "layers.38.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.38.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.38.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.38.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
+    "layers.38.self_attn.k_proj.bias": "model-00015-of-00030.safetensors",
+    "layers.38.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.38.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.38.self_attn.q_proj.bias": "model-00015-of-00030.safetensors",
+    "layers.38.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.38.self_attn.v_proj.bias": "model-00015-of-00030.safetensors",
+    "layers.38.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.39.input_layernorm.weight": "model-00016-of-00030.safetensors",
+    "layers.39.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.39.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.39.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.39.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
+    "layers.39.self_attn.k_proj.bias": "model-00015-of-00030.safetensors",
+    "layers.39.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.39.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.39.self_attn.q_proj.bias": "model-00015-of-00030.safetensors",
+    "layers.39.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.39.self_attn.v_proj.bias": "model-00015-of-00030.safetensors",
+    "layers.39.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
+    "layers.4.input_layernorm.weight": "model-00003-of-00030.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
+    "layers.4.self_attn.k_proj.bias": "model-00003-of-00030.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.4.self_attn.q_proj.bias": "model-00003-of-00030.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.4.self_attn.v_proj.bias": "model-00003-of-00030.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.40.input_layernorm.weight": "model-00016-of-00030.safetensors",
+    "layers.40.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.40.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.40.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.40.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
+    "layers.40.self_attn.k_proj.bias": "model-00016-of-00030.safetensors",
+    "layers.40.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.40.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.40.self_attn.q_proj.bias": "model-00016-of-00030.safetensors",
+    "layers.40.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.40.self_attn.v_proj.bias": "model-00016-of-00030.safetensors",
+    "layers.40.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.41.input_layernorm.weight": "model-00016-of-00030.safetensors",
+    "layers.41.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.41.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.41.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.41.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
+    "layers.41.self_attn.k_proj.bias": "model-00016-of-00030.safetensors",
+    "layers.41.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.41.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.41.self_attn.q_proj.bias": "model-00016-of-00030.safetensors",
+    "layers.41.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.41.self_attn.v_proj.bias": "model-00016-of-00030.safetensors",
+    "layers.41.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.42.input_layernorm.weight": "model-00017-of-00030.safetensors",
+    "layers.42.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.42.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.42.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.42.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
+    "layers.42.self_attn.k_proj.bias": "model-00016-of-00030.safetensors",
+    "layers.42.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.42.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.42.self_attn.q_proj.bias": "model-00016-of-00030.safetensors",
+    "layers.42.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.42.self_attn.v_proj.bias": "model-00016-of-00030.safetensors",
+    "layers.42.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
+    "layers.43.input_layernorm.weight": "model-00017-of-00030.safetensors",
+    "layers.43.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.43.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.43.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.43.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
+    "layers.43.self_attn.k_proj.bias": "model-00017-of-00030.safetensors",
+    "layers.43.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.43.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.43.self_attn.q_proj.bias": "model-00017-of-00030.safetensors",
+    "layers.43.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.43.self_attn.v_proj.bias": "model-00017-of-00030.safetensors",
+    "layers.43.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.44.input_layernorm.weight": "model-00017-of-00030.safetensors",
+    "layers.44.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.44.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.44.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.44.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
+    "layers.44.self_attn.k_proj.bias": "model-00017-of-00030.safetensors",
+    "layers.44.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.44.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.44.self_attn.q_proj.bias": "model-00017-of-00030.safetensors",
+    "layers.44.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.44.self_attn.v_proj.bias": "model-00017-of-00030.safetensors",
+    "layers.44.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.45.input_layernorm.weight": "model-00018-of-00030.safetensors",
+    "layers.45.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.45.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.45.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.45.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
+    "layers.45.self_attn.k_proj.bias": "model-00017-of-00030.safetensors",
+    "layers.45.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.45.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.45.self_attn.q_proj.bias": "model-00017-of-00030.safetensors",
+    "layers.45.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.45.self_attn.v_proj.bias": "model-00017-of-00030.safetensors",
+    "layers.45.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
+    "layers.46.input_layernorm.weight": "model-00018-of-00030.safetensors",
+    "layers.46.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.46.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.46.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.46.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
+    "layers.46.self_attn.k_proj.bias": "model-00018-of-00030.safetensors",
+    "layers.46.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.46.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.46.self_attn.q_proj.bias": "model-00018-of-00030.safetensors",
+    "layers.46.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.46.self_attn.v_proj.bias": "model-00018-of-00030.safetensors",
+    "layers.46.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.47.input_layernorm.weight": "model-00018-of-00030.safetensors",
+    "layers.47.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.47.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.47.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.47.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
+    "layers.47.self_attn.k_proj.bias": "model-00018-of-00030.safetensors",
+    "layers.47.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.47.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.47.self_attn.q_proj.bias": "model-00018-of-00030.safetensors",
+    "layers.47.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.47.self_attn.v_proj.bias": "model-00018-of-00030.safetensors",
+    "layers.47.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
+    "layers.48.input_layernorm.weight": "model-00019-of-00030.safetensors",
+    "layers.48.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.48.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.48.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.48.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
+    "layers.48.self_attn.k_proj.bias": "model-00019-of-00030.safetensors",
+    "layers.48.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.48.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.48.self_attn.q_proj.bias": "model-00019-of-00030.safetensors",
+    "layers.48.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.48.self_attn.v_proj.bias": "model-00019-of-00030.safetensors",
+    "layers.48.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.49.input_layernorm.weight": "model-00019-of-00030.safetensors",
+    "layers.49.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.49.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.49.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.49.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
+    "layers.49.self_attn.k_proj.bias": "model-00019-of-00030.safetensors",
+    "layers.49.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.49.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.49.self_attn.q_proj.bias": "model-00019-of-00030.safetensors",
+    "layers.49.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.49.self_attn.v_proj.bias": "model-00019-of-00030.safetensors",
+    "layers.49.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.5.input_layernorm.weight": "model-00003-of-00030.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
+    "layers.5.self_attn.k_proj.bias": "model-00003-of-00030.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.5.self_attn.q_proj.bias": "model-00003-of-00030.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.5.self_attn.v_proj.bias": "model-00003-of-00030.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.50.input_layernorm.weight": "model-00020-of-00030.safetensors",
+    "layers.50.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.50.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.50.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.50.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
+    "layers.50.self_attn.k_proj.bias": "model-00019-of-00030.safetensors",
+    "layers.50.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.50.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.50.self_attn.q_proj.bias": "model-00019-of-00030.safetensors",
+    "layers.50.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.50.self_attn.v_proj.bias": "model-00019-of-00030.safetensors",
+    "layers.50.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
+    "layers.51.input_layernorm.weight": "model-00020-of-00030.safetensors",
+    "layers.51.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.51.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.51.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.51.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
+    "layers.51.self_attn.k_proj.bias": "model-00020-of-00030.safetensors",
+    "layers.51.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.51.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.51.self_attn.q_proj.bias": "model-00020-of-00030.safetensors",
+    "layers.51.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.51.self_attn.v_proj.bias": "model-00020-of-00030.safetensors",
+    "layers.51.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.52.input_layernorm.weight": "model-00020-of-00030.safetensors",
+    "layers.52.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.52.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.52.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.52.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
+    "layers.52.self_attn.k_proj.bias": "model-00020-of-00030.safetensors",
+    "layers.52.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.52.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.52.self_attn.q_proj.bias": "model-00020-of-00030.safetensors",
+    "layers.52.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.52.self_attn.v_proj.bias": "model-00020-of-00030.safetensors",
+    "layers.52.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.53.input_layernorm.weight": "model-00021-of-00030.safetensors",
+    "layers.53.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.53.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.53.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.53.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
+    "layers.53.self_attn.k_proj.bias": "model-00020-of-00030.safetensors",
+    "layers.53.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.53.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.53.self_attn.q_proj.bias": "model-00020-of-00030.safetensors",
+    "layers.53.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.53.self_attn.v_proj.bias": "model-00020-of-00030.safetensors",
+    "layers.53.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
+    "layers.54.input_layernorm.weight": "model-00021-of-00030.safetensors",
+    "layers.54.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.54.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.54.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.54.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
+    "layers.54.self_attn.k_proj.bias": "model-00021-of-00030.safetensors",
+    "layers.54.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.54.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.54.self_attn.q_proj.bias": "model-00021-of-00030.safetensors",
+    "layers.54.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.54.self_attn.v_proj.bias": "model-00021-of-00030.safetensors",
+    "layers.54.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.55.input_layernorm.weight": "model-00021-of-00030.safetensors",
+    "layers.55.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.55.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.55.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.55.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
+    "layers.55.self_attn.k_proj.bias": "model-00021-of-00030.safetensors",
+    "layers.55.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.55.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.55.self_attn.q_proj.bias": "model-00021-of-00030.safetensors",
+    "layers.55.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.55.self_attn.v_proj.bias": "model-00021-of-00030.safetensors",
+    "layers.55.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.56.input_layernorm.weight": "model-00022-of-00030.safetensors",
+    "layers.56.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.56.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.56.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.56.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
+    "layers.56.self_attn.k_proj.bias": "model-00021-of-00030.safetensors",
+    "layers.56.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.56.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.56.self_attn.q_proj.bias": "model-00021-of-00030.safetensors",
+    "layers.56.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.56.self_attn.v_proj.bias": "model-00021-of-00030.safetensors",
+    "layers.56.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
+    "layers.57.input_layernorm.weight": "model-00022-of-00030.safetensors",
+    "layers.57.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.57.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.57.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.57.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
+    "layers.57.self_attn.k_proj.bias": "model-00022-of-00030.safetensors",
+    "layers.57.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.57.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.57.self_attn.q_proj.bias": "model-00022-of-00030.safetensors",
+    "layers.57.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.57.self_attn.v_proj.bias": "model-00022-of-00030.safetensors",
+    "layers.57.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.58.input_layernorm.weight": "model-00022-of-00030.safetensors",
+    "layers.58.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.58.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.58.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.58.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
+    "layers.58.self_attn.k_proj.bias": "model-00022-of-00030.safetensors",
+    "layers.58.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.58.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.58.self_attn.q_proj.bias": "model-00022-of-00030.safetensors",
+    "layers.58.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.58.self_attn.v_proj.bias": "model-00022-of-00030.safetensors",
+    "layers.58.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
+    "layers.59.input_layernorm.weight": "model-00023-of-00030.safetensors",
+    "layers.59.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.59.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.59.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.59.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
+    "layers.59.self_attn.k_proj.bias": "model-00023-of-00030.safetensors",
+    "layers.59.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.59.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.59.self_attn.q_proj.bias": "model-00023-of-00030.safetensors",
+    "layers.59.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.59.self_attn.v_proj.bias": "model-00023-of-00030.safetensors",
+    "layers.59.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.6.input_layernorm.weight": "model-00004-of-00030.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
+    "layers.6.self_attn.k_proj.bias": "model-00003-of-00030.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.6.self_attn.q_proj.bias": "model-00003-of-00030.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.6.self_attn.v_proj.bias": "model-00003-of-00030.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
+    "layers.60.input_layernorm.weight": "model-00023-of-00030.safetensors",
+    "layers.60.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.60.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.60.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.60.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
+    "layers.60.self_attn.k_proj.bias": "model-00023-of-00030.safetensors",
+    "layers.60.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.60.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.60.self_attn.q_proj.bias": "model-00023-of-00030.safetensors",
+    "layers.60.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.60.self_attn.v_proj.bias": "model-00023-of-00030.safetensors",
+    "layers.60.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.61.input_layernorm.weight": "model-00024-of-00030.safetensors",
+    "layers.61.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.61.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.61.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.61.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
+    "layers.61.self_attn.k_proj.bias": "model-00023-of-00030.safetensors",
+    "layers.61.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.61.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.61.self_attn.q_proj.bias": "model-00023-of-00030.safetensors",
+    "layers.61.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.61.self_attn.v_proj.bias": "model-00023-of-00030.safetensors",
+    "layers.61.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
+    "layers.62.input_layernorm.weight": "model-00024-of-00030.safetensors",
+    "layers.62.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.62.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.62.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.62.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
+    "layers.62.self_attn.k_proj.bias": "model-00024-of-00030.safetensors",
+    "layers.62.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.62.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.62.self_attn.q_proj.bias": "model-00024-of-00030.safetensors",
+    "layers.62.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.62.self_attn.v_proj.bias": "model-00024-of-00030.safetensors",
+    "layers.62.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.63.input_layernorm.weight": "model-00024-of-00030.safetensors",
+    "layers.63.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.63.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.63.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.63.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
+    "layers.63.self_attn.k_proj.bias": "model-00024-of-00030.safetensors",
+    "layers.63.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.63.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.63.self_attn.q_proj.bias": "model-00024-of-00030.safetensors",
+    "layers.63.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.63.self_attn.v_proj.bias": "model-00024-of-00030.safetensors",
+    "layers.63.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.64.input_layernorm.weight": "model-00025-of-00030.safetensors",
+    "layers.64.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.64.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.64.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.64.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
+    "layers.64.self_attn.k_proj.bias": "model-00024-of-00030.safetensors",
+    "layers.64.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.64.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.64.self_attn.q_proj.bias": "model-00024-of-00030.safetensors",
+    "layers.64.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.64.self_attn.v_proj.bias": "model-00024-of-00030.safetensors",
+    "layers.64.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
+    "layers.65.input_layernorm.weight": "model-00025-of-00030.safetensors",
+    "layers.65.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.65.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.65.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.65.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
+    "layers.65.self_attn.k_proj.bias": "model-00025-of-00030.safetensors",
+    "layers.65.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.65.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.65.self_attn.q_proj.bias": "model-00025-of-00030.safetensors",
+    "layers.65.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.65.self_attn.v_proj.bias": "model-00025-of-00030.safetensors",
+    "layers.65.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.66.input_layernorm.weight": "model-00025-of-00030.safetensors",
+    "layers.66.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.66.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.66.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.66.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
+    "layers.66.self_attn.k_proj.bias": "model-00025-of-00030.safetensors",
+    "layers.66.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.66.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.66.self_attn.q_proj.bias": "model-00025-of-00030.safetensors",
+    "layers.66.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.66.self_attn.v_proj.bias": "model-00025-of-00030.safetensors",
+    "layers.66.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.67.input_layernorm.weight": "model-00026-of-00030.safetensors",
+    "layers.67.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.67.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.67.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.67.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
+    "layers.67.self_attn.k_proj.bias": "model-00025-of-00030.safetensors",
+    "layers.67.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.67.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.67.self_attn.q_proj.bias": "model-00025-of-00030.safetensors",
+    "layers.67.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.67.self_attn.v_proj.bias": "model-00025-of-00030.safetensors",
+    "layers.67.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
+    "layers.68.input_layernorm.weight": "model-00026-of-00030.safetensors",
+    "layers.68.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.68.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.68.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.68.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
+    "layers.68.self_attn.k_proj.bias": "model-00026-of-00030.safetensors",
+    "layers.68.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.68.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.68.self_attn.q_proj.bias": "model-00026-of-00030.safetensors",
+    "layers.68.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.68.self_attn.v_proj.bias": "model-00026-of-00030.safetensors",
+    "layers.68.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.69.input_layernorm.weight": "model-00026-of-00030.safetensors",
+    "layers.69.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.69.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.69.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.69.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
+    "layers.69.self_attn.k_proj.bias": "model-00026-of-00030.safetensors",
+    "layers.69.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.69.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.69.self_attn.q_proj.bias": "model-00026-of-00030.safetensors",
+    "layers.69.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.69.self_attn.v_proj.bias": "model-00026-of-00030.safetensors",
+    "layers.69.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
+    "layers.7.input_layernorm.weight": "model-00004-of-00030.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
+    "layers.7.self_attn.k_proj.bias": "model-00004-of-00030.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.7.self_attn.q_proj.bias": "model-00004-of-00030.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.7.self_attn.v_proj.bias": "model-00004-of-00030.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.70.input_layernorm.weight": "model-00027-of-00030.safetensors",
+    "layers.70.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.70.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.70.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.70.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
+    "layers.70.self_attn.k_proj.bias": "model-00027-of-00030.safetensors",
+    "layers.70.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.70.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.70.self_attn.q_proj.bias": "model-00027-of-00030.safetensors",
+    "layers.70.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.70.self_attn.v_proj.bias": "model-00027-of-00030.safetensors",
+    "layers.70.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.71.input_layernorm.weight": "model-00027-of-00030.safetensors",
+    "layers.71.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.71.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.71.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.71.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
+    "layers.71.self_attn.k_proj.bias": "model-00027-of-00030.safetensors",
+    "layers.71.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.71.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.71.self_attn.q_proj.bias": "model-00027-of-00030.safetensors",
+    "layers.71.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.71.self_attn.v_proj.bias": "model-00027-of-00030.safetensors",
+    "layers.71.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.72.input_layernorm.weight": "model-00028-of-00030.safetensors",
+    "layers.72.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.72.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.72.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.72.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
+    "layers.72.self_attn.k_proj.bias": "model-00027-of-00030.safetensors",
+    "layers.72.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.72.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.72.self_attn.q_proj.bias": "model-00027-of-00030.safetensors",
+    "layers.72.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.72.self_attn.v_proj.bias": "model-00027-of-00030.safetensors",
+    "layers.72.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
+    "layers.73.input_layernorm.weight": "model-00028-of-00030.safetensors",
+    "layers.73.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.73.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.73.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.73.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
+    "layers.73.self_attn.k_proj.bias": "model-00028-of-00030.safetensors",
+    "layers.73.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.73.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.73.self_attn.q_proj.bias": "model-00028-of-00030.safetensors",
+    "layers.73.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.73.self_attn.v_proj.bias": "model-00028-of-00030.safetensors",
+    "layers.73.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.74.input_layernorm.weight": "model-00028-of-00030.safetensors",
+    "layers.74.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.74.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.74.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.74.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
+    "layers.74.self_attn.k_proj.bias": "model-00028-of-00030.safetensors",
+    "layers.74.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.74.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.74.self_attn.q_proj.bias": "model-00028-of-00030.safetensors",
+    "layers.74.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.74.self_attn.v_proj.bias": "model-00028-of-00030.safetensors",
+    "layers.74.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.75.input_layernorm.weight": "model-00029-of-00030.safetensors",
+    "layers.75.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.75.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.75.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.75.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
+    "layers.75.self_attn.k_proj.bias": "model-00028-of-00030.safetensors",
+    "layers.75.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.75.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.75.self_attn.q_proj.bias": "model-00028-of-00030.safetensors",
+    "layers.75.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.75.self_attn.v_proj.bias": "model-00028-of-00030.safetensors",
+    "layers.75.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
+    "layers.76.input_layernorm.weight": "model-00029-of-00030.safetensors",
+    "layers.76.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.76.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.76.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.76.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
+    "layers.76.self_attn.k_proj.bias": "model-00029-of-00030.safetensors",
+    "layers.76.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.76.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.76.self_attn.q_proj.bias": "model-00029-of-00030.safetensors",
+    "layers.76.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.76.self_attn.v_proj.bias": "model-00029-of-00030.safetensors",
+    "layers.76.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.77.input_layernorm.weight": "model-00029-of-00030.safetensors",
+    "layers.77.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.77.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.77.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.77.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
+    "layers.77.self_attn.k_proj.bias": "model-00029-of-00030.safetensors",
+    "layers.77.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.77.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.77.self_attn.q_proj.bias": "model-00029-of-00030.safetensors",
+    "layers.77.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.77.self_attn.v_proj.bias": "model-00029-of-00030.safetensors",
+    "layers.77.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.78.input_layernorm.weight": "model-00030-of-00030.safetensors",
+    "layers.78.mlp.down_proj.weight": "model-00030-of-00030.safetensors",
+    "layers.78.mlp.gate_proj.weight": "model-00030-of-00030.safetensors",
+    "layers.78.mlp.up_proj.weight": "model-00030-of-00030.safetensors",
+    "layers.78.post_attention_layernorm.weight": "model-00030-of-00030.safetensors",
+    "layers.78.self_attn.k_proj.bias": "model-00029-of-00030.safetensors",
+    "layers.78.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.78.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.78.self_attn.q_proj.bias": "model-00029-of-00030.safetensors",
+    "layers.78.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.78.self_attn.v_proj.bias": "model-00029-of-00030.safetensors",
+    "layers.78.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
+    "layers.79.input_layernorm.weight": "model-00030-of-00030.safetensors",
+    "layers.79.mlp.down_proj.weight": "model-00030-of-00030.safetensors",
+    "layers.79.mlp.gate_proj.weight": "model-00030-of-00030.safetensors",
+    "layers.79.mlp.up_proj.weight": "model-00030-of-00030.safetensors",
+    "layers.79.post_attention_layernorm.weight": "model-00030-of-00030.safetensors",
+    "layers.79.self_attn.k_proj.bias": "model-00030-of-00030.safetensors",
+    "layers.79.self_attn.k_proj.weight": "model-00030-of-00030.safetensors",
+    "layers.79.self_attn.o_proj.weight": "model-00030-of-00030.safetensors",
+    "layers.79.self_attn.q_proj.bias": "model-00030-of-00030.safetensors",
+    "layers.79.self_attn.q_proj.weight": "model-00030-of-00030.safetensors",
+    "layers.79.self_attn.v_proj.bias": "model-00030-of-00030.safetensors",
+    "layers.79.self_attn.v_proj.weight": "model-00030-of-00030.safetensors",
+    "layers.8.input_layernorm.weight": "model-00004-of-00030.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
+    "layers.8.self_attn.k_proj.bias": "model-00004-of-00030.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.8.self_attn.q_proj.bias": "model-00004-of-00030.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.8.self_attn.v_proj.bias": "model-00004-of-00030.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.9.input_layernorm.weight": "model-00005-of-00030.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
+    "layers.9.self_attn.k_proj.bias": "model-00004-of-00030.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.9.self_attn.q_proj.bias": "model-00004-of-00030.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
+    "layers.9.self_attn.v_proj.bias": "model-00004-of-00030.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
+    "norm.weight": "model-00030-of-00030.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 12845056,
+    "min_pixels": 3136
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd8c258c419667ebe0fb2fdb04f0f374292349d5deba1cba179d29177e80fc0
+size 11421997

tokenizer_config.json

@@ -0,0 +1,213 @@
+{
+  "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 image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": 131072,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": null
+}