Upload folder using huggingface_hub
Browse files- chat_template.jinja +2 -2
- chat_template.json +3 -0
- config.json +1 -4
- generation_config.json +13 -11
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +361 -362
- tokenizer_config.json +1 -1
chat_template.jinja
CHANGED
|
@@ -60,8 +60,8 @@
|
|
| 60 |
{%- set reasoning_content = message.reasoning_content %}
|
| 61 |
{%- else %}
|
| 62 |
{%- if '</think>' in content %}
|
| 63 |
-
{%- set reasoning_content = content.split('</think>')
|
| 64 |
-
{%- set content = content.split('</think>')
|
| 65 |
{%- endif %}
|
| 66 |
{%- endif %}
|
| 67 |
{%- if loop.index0 > ns.last_query_index %}
|
|
|
|
| 60 |
{%- set reasoning_content = message.reasoning_content %}
|
| 61 |
{%- else %}
|
| 62 |
{%- if '</think>' in content %}
|
| 63 |
+
{%- set reasoning_content = ((content.split('</think>')|first).rstrip('\n').split('<think>')|last).lstrip('\n') %}
|
| 64 |
+
{%- set content = (content.split('</think>')|last).lstrip('\n') %}
|
| 65 |
{%- endif %}
|
| 66 |
{%- endif %}
|
| 67 |
{%- if loop.index0 > ns.last_query_index %}
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count) %}\n {%- if content is string %}\n {{- content }}\n {%- else %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n{%- endmacro %}\n{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- render_content(messages[0].content, false) + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + render_content(messages[0].content, false) + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false) %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, True) %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}\n"
|
| 3 |
+
}
|
config.json
CHANGED
|
@@ -2,8 +2,6 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen3VLForConditionalGeneration"
|
| 4 |
],
|
| 5 |
-
"torch_dtype": "bfloat16",
|
| 6 |
-
"eos_token_id": 151645,
|
| 7 |
"image_token_id": 151655,
|
| 8 |
"model_type": "qwen3_vl",
|
| 9 |
"pad_token_id": 151654,
|
|
@@ -49,7 +47,6 @@
|
|
| 49 |
17
|
| 50 |
],
|
| 51 |
"depth": 24,
|
| 52 |
-
"torch_dtype": "bfloat16",
|
| 53 |
"hidden_act": "gelu_pytorch_tanh",
|
| 54 |
"hidden_size": 1024,
|
| 55 |
"in_channels": 3,
|
|
@@ -65,4 +62,4 @@
|
|
| 65 |
},
|
| 66 |
"vision_end_token_id": 151653,
|
| 67 |
"vision_start_token_id": 151652
|
| 68 |
-
}
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen3VLForConditionalGeneration"
|
| 4 |
],
|
|
|
|
|
|
|
| 5 |
"image_token_id": 151655,
|
| 6 |
"model_type": "qwen3_vl",
|
| 7 |
"pad_token_id": 151654,
|
|
|
|
| 47 |
17
|
| 48 |
],
|
| 49 |
"depth": 24,
|
|
|
|
| 50 |
"hidden_act": "gelu_pytorch_tanh",
|
| 51 |
"hidden_size": 1024,
|
| 52 |
"in_channels": 3,
|
|
|
|
| 62 |
},
|
| 63 |
"vision_end_token_id": 151653,
|
| 64 |
"vision_start_token_id": 151652
|
| 65 |
+
}
|
generation_config.json
CHANGED
|
@@ -1,12 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
|
|
|
|
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"pad_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"top_k": 20,
|
| 10 |
+
"top_p": 0.95,
|
| 11 |
+
"repetition_penalty": 1.0,
|
| 12 |
+
"temperature": 1.0,
|
| 13 |
+
"transformers_version": "4.56.0"
|
| 14 |
+
}
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02cab5e606c91e5ede7b1a70c49fa5abc58c77692362ee3be2e6656fd1327793
|
| 3 |
+
size 4967229296
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:000ef17ec19fdd0531d825080c896c86025bc93036de1f34e3d133fa71c2cccf
|
| 3 |
+
size 3908490048
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,5 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_parameters": 4437815808,
|
| 4 |
"total_size": 8875631616
|
| 5 |
},
|
| 6 |
"weight_map": {
|
|
@@ -93,50 +92,50 @@
|
|
| 93 |
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 94 |
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
-
"model.language_model.layers.16.input_layernorm.weight": "model-
|
| 97 |
-
"model.language_model.layers.16.mlp.down_proj.weight": "model-
|
| 98 |
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
"model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
-
"model.language_model.layers.16.post_attention_layernorm.weight": "model-
|
| 101 |
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
-
"model.language_model.layers.17.input_layernorm.weight": "model-
|
| 108 |
-
"model.language_model.layers.17.mlp.down_proj.weight": "model-
|
| 109 |
-
"model.language_model.layers.17.mlp.gate_proj.weight": "model-
|
| 110 |
-
"model.language_model.layers.17.mlp.up_proj.weight": "model-
|
| 111 |
-
"model.language_model.layers.17.post_attention_layernorm.weight": "model-
|
| 112 |
-
"model.language_model.layers.17.self_attn.k_norm.weight": "model-
|
| 113 |
-
"model.language_model.layers.17.self_attn.k_proj.weight": "model-
|
| 114 |
-
"model.language_model.layers.17.self_attn.o_proj.weight": "model-
|
| 115 |
-
"model.language_model.layers.17.self_attn.q_norm.weight": "model-
|
| 116 |
-
"model.language_model.layers.17.self_attn.q_proj.weight": "model-
|
| 117 |
-
"model.language_model.layers.17.self_attn.v_proj.weight": "model-
|
| 118 |
-
"model.language_model.layers.18.input_layernorm.weight": "model-
|
| 119 |
-
"model.language_model.layers.18.mlp.down_proj.weight": "model-
|
| 120 |
-
"model.language_model.layers.18.mlp.gate_proj.weight": "model-
|
| 121 |
-
"model.language_model.layers.18.mlp.up_proj.weight": "model-
|
| 122 |
-
"model.language_model.layers.18.post_attention_layernorm.weight": "model-
|
| 123 |
-
"model.language_model.layers.18.self_attn.k_norm.weight": "model-
|
| 124 |
-
"model.language_model.layers.18.self_attn.k_proj.weight": "model-
|
| 125 |
-
"model.language_model.layers.18.self_attn.o_proj.weight": "model-
|
| 126 |
-
"model.language_model.layers.18.self_attn.q_norm.weight": "model-
|
| 127 |
-
"model.language_model.layers.18.self_attn.q_proj.weight": "model-
|
| 128 |
-
"model.language_model.layers.18.self_attn.v_proj.weight": "model-
|
| 129 |
-
"model.language_model.layers.19.input_layernorm.weight": "model-
|
| 130 |
-
"model.language_model.layers.19.mlp.down_proj.weight": "model-
|
| 131 |
-
"model.language_model.layers.19.mlp.gate_proj.weight": "model-
|
| 132 |
-
"model.language_model.layers.19.mlp.up_proj.weight": "model-
|
| 133 |
-
"model.language_model.layers.19.post_attention_layernorm.weight": "model-
|
| 134 |
-
"model.language_model.layers.19.self_attn.k_norm.weight": "model-
|
| 135 |
-
"model.language_model.layers.19.self_attn.k_proj.weight": "model-
|
| 136 |
-
"model.language_model.layers.19.self_attn.o_proj.weight": "model-
|
| 137 |
-
"model.language_model.layers.19.self_attn.q_norm.weight": "model-
|
| 138 |
-
"model.language_model.layers.19.self_attn.q_proj.weight": "model-
|
| 139 |
-
"model.language_model.layers.19.self_attn.v_proj.weight": "model-
|
| 140 |
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -148,17 +147,17 @@
|
|
| 148 |
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 149 |
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
-
"model.language_model.layers.20.input_layernorm.weight": "model-
|
| 152 |
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
-
"model.language_model.layers.20.mlp.gate_proj.weight": "model-
|
| 154 |
-
"model.language_model.layers.20.mlp.up_proj.weight": "model-
|
| 155 |
-
"model.language_model.layers.20.post_attention_layernorm.weight": "model-
|
| 156 |
-
"model.language_model.layers.20.self_attn.k_norm.weight": "model-
|
| 157 |
-
"model.language_model.layers.20.self_attn.k_proj.weight": "model-
|
| 158 |
-
"model.language_model.layers.20.self_attn.o_proj.weight": "model-
|
| 159 |
-
"model.language_model.layers.20.self_attn.q_norm.weight": "model-
|
| 160 |
-
"model.language_model.layers.20.self_attn.q_proj.weight": "model-
|
| 161 |
-
"model.language_model.layers.20.self_attn.v_proj.weight": "model-
|
| 162 |
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 163 |
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
@@ -402,320 +401,320 @@
|
|
| 402 |
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 405 |
-
"model.visual.blocks.0.attn.proj.bias": "model-
|
| 406 |
-
"model.visual.blocks.0.attn.proj.weight": "model-
|
| 407 |
-
"model.visual.blocks.0.attn.qkv.bias": "model-
|
| 408 |
-
"model.visual.blocks.0.attn.qkv.weight": "model-
|
| 409 |
-
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-
|
| 410 |
-
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-
|
| 411 |
-
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-
|
| 412 |
-
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-
|
| 413 |
-
"model.visual.blocks.0.norm1.bias": "model-
|
| 414 |
-
"model.visual.blocks.0.norm1.weight": "model-
|
| 415 |
-
"model.visual.blocks.0.norm2.bias": "model-
|
| 416 |
-
"model.visual.blocks.0.norm2.weight": "model-
|
| 417 |
-
"model.visual.blocks.1.attn.proj.bias": "model-
|
| 418 |
-
"model.visual.blocks.1.attn.proj.weight": "model-
|
| 419 |
-
"model.visual.blocks.1.attn.qkv.bias": "model-
|
| 420 |
-
"model.visual.blocks.1.attn.qkv.weight": "model-
|
| 421 |
-
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-
|
| 422 |
-
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-
|
| 423 |
-
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-
|
| 424 |
-
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-
|
| 425 |
-
"model.visual.blocks.1.norm1.bias": "model-
|
| 426 |
-
"model.visual.blocks.1.norm1.weight": "model-
|
| 427 |
-
"model.visual.blocks.1.norm2.bias": "model-
|
| 428 |
-
"model.visual.blocks.1.norm2.weight": "model-
|
| 429 |
-
"model.visual.blocks.10.attn.proj.bias": "model-
|
| 430 |
-
"model.visual.blocks.10.attn.proj.weight": "model-
|
| 431 |
-
"model.visual.blocks.10.attn.qkv.bias": "model-
|
| 432 |
-
"model.visual.blocks.10.attn.qkv.weight": "model-
|
| 433 |
-
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-
|
| 434 |
-
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-
|
| 435 |
-
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-
|
| 436 |
-
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-
|
| 437 |
-
"model.visual.blocks.10.norm1.bias": "model-
|
| 438 |
-
"model.visual.blocks.10.norm1.weight": "model-
|
| 439 |
-
"model.visual.blocks.10.norm2.bias": "model-
|
| 440 |
-
"model.visual.blocks.10.norm2.weight": "model-
|
| 441 |
-
"model.visual.blocks.11.attn.proj.bias": "model-
|
| 442 |
-
"model.visual.blocks.11.attn.proj.weight": "model-
|
| 443 |
-
"model.visual.blocks.11.attn.qkv.bias": "model-
|
| 444 |
-
"model.visual.blocks.11.attn.qkv.weight": "model-
|
| 445 |
-
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-
|
| 446 |
-
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-
|
| 447 |
-
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-
|
| 448 |
-
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-
|
| 449 |
-
"model.visual.blocks.11.norm1.bias": "model-
|
| 450 |
-
"model.visual.blocks.11.norm1.weight": "model-
|
| 451 |
-
"model.visual.blocks.11.norm2.bias": "model-
|
| 452 |
-
"model.visual.blocks.11.norm2.weight": "model-
|
| 453 |
-
"model.visual.blocks.12.attn.proj.bias": "model-
|
| 454 |
-
"model.visual.blocks.12.attn.proj.weight": "model-
|
| 455 |
-
"model.visual.blocks.12.attn.qkv.bias": "model-
|
| 456 |
-
"model.visual.blocks.12.attn.qkv.weight": "model-
|
| 457 |
-
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-
|
| 458 |
-
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-
|
| 459 |
-
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-
|
| 460 |
-
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-
|
| 461 |
-
"model.visual.blocks.12.norm1.bias": "model-
|
| 462 |
-
"model.visual.blocks.12.norm1.weight": "model-
|
| 463 |
-
"model.visual.blocks.12.norm2.bias": "model-
|
| 464 |
-
"model.visual.blocks.12.norm2.weight": "model-
|
| 465 |
-
"model.visual.blocks.13.attn.proj.bias": "model-
|
| 466 |
-
"model.visual.blocks.13.attn.proj.weight": "model-
|
| 467 |
-
"model.visual.blocks.13.attn.qkv.bias": "model-
|
| 468 |
-
"model.visual.blocks.13.attn.qkv.weight": "model-
|
| 469 |
-
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-
|
| 470 |
-
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-
|
| 471 |
-
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-
|
| 472 |
-
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-
|
| 473 |
-
"model.visual.blocks.13.norm1.bias": "model-
|
| 474 |
-
"model.visual.blocks.13.norm1.weight": "model-
|
| 475 |
-
"model.visual.blocks.13.norm2.bias": "model-
|
| 476 |
-
"model.visual.blocks.13.norm2.weight": "model-
|
| 477 |
-
"model.visual.blocks.14.attn.proj.bias": "model-
|
| 478 |
-
"model.visual.blocks.14.attn.proj.weight": "model-
|
| 479 |
-
"model.visual.blocks.14.attn.qkv.bias": "model-
|
| 480 |
-
"model.visual.blocks.14.attn.qkv.weight": "model-
|
| 481 |
-
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-
|
| 482 |
-
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-
|
| 483 |
-
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-
|
| 484 |
-
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-
|
| 485 |
-
"model.visual.blocks.14.norm1.bias": "model-
|
| 486 |
-
"model.visual.blocks.14.norm1.weight": "model-
|
| 487 |
-
"model.visual.blocks.14.norm2.bias": "model-
|
| 488 |
-
"model.visual.blocks.14.norm2.weight": "model-
|
| 489 |
-
"model.visual.blocks.15.attn.proj.bias": "model-
|
| 490 |
-
"model.visual.blocks.15.attn.proj.weight": "model-
|
| 491 |
-
"model.visual.blocks.15.attn.qkv.bias": "model-
|
| 492 |
-
"model.visual.blocks.15.attn.qkv.weight": "model-
|
| 493 |
-
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-
|
| 494 |
-
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-
|
| 495 |
-
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-
|
| 496 |
-
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-
|
| 497 |
-
"model.visual.blocks.15.norm1.bias": "model-
|
| 498 |
-
"model.visual.blocks.15.norm1.weight": "model-
|
| 499 |
-
"model.visual.blocks.15.norm2.bias": "model-
|
| 500 |
-
"model.visual.blocks.15.norm2.weight": "model-
|
| 501 |
-
"model.visual.blocks.16.attn.proj.bias": "model-
|
| 502 |
-
"model.visual.blocks.16.attn.proj.weight": "model-
|
| 503 |
-
"model.visual.blocks.16.attn.qkv.bias": "model-
|
| 504 |
-
"model.visual.blocks.16.attn.qkv.weight": "model-
|
| 505 |
-
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-
|
| 506 |
-
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-
|
| 507 |
-
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-
|
| 508 |
-
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-
|
| 509 |
-
"model.visual.blocks.16.norm1.bias": "model-
|
| 510 |
-
"model.visual.blocks.16.norm1.weight": "model-
|
| 511 |
-
"model.visual.blocks.16.norm2.bias": "model-
|
| 512 |
-
"model.visual.blocks.16.norm2.weight": "model-
|
| 513 |
-
"model.visual.blocks.17.attn.proj.bias": "model-
|
| 514 |
-
"model.visual.blocks.17.attn.proj.weight": "model-
|
| 515 |
-
"model.visual.blocks.17.attn.qkv.bias": "model-
|
| 516 |
-
"model.visual.blocks.17.attn.qkv.weight": "model-
|
| 517 |
-
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-
|
| 518 |
-
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-
|
| 519 |
-
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-
|
| 520 |
-
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-
|
| 521 |
-
"model.visual.blocks.17.norm1.bias": "model-
|
| 522 |
-
"model.visual.blocks.17.norm1.weight": "model-
|
| 523 |
-
"model.visual.blocks.17.norm2.bias": "model-
|
| 524 |
-
"model.visual.blocks.17.norm2.weight": "model-
|
| 525 |
-
"model.visual.blocks.18.attn.proj.bias": "model-
|
| 526 |
-
"model.visual.blocks.18.attn.proj.weight": "model-
|
| 527 |
-
"model.visual.blocks.18.attn.qkv.bias": "model-
|
| 528 |
-
"model.visual.blocks.18.attn.qkv.weight": "model-
|
| 529 |
-
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-
|
| 530 |
-
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-
|
| 531 |
-
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-
|
| 532 |
-
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-
|
| 533 |
-
"model.visual.blocks.18.norm1.bias": "model-
|
| 534 |
-
"model.visual.blocks.18.norm1.weight": "model-
|
| 535 |
-
"model.visual.blocks.18.norm2.bias": "model-
|
| 536 |
-
"model.visual.blocks.18.norm2.weight": "model-
|
| 537 |
-
"model.visual.blocks.19.attn.proj.bias": "model-
|
| 538 |
-
"model.visual.blocks.19.attn.proj.weight": "model-
|
| 539 |
-
"model.visual.blocks.19.attn.qkv.bias": "model-
|
| 540 |
-
"model.visual.blocks.19.attn.qkv.weight": "model-
|
| 541 |
-
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-
|
| 542 |
-
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-
|
| 543 |
-
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-
|
| 544 |
-
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-
|
| 545 |
-
"model.visual.blocks.19.norm1.bias": "model-
|
| 546 |
-
"model.visual.blocks.19.norm1.weight": "model-
|
| 547 |
-
"model.visual.blocks.19.norm2.bias": "model-
|
| 548 |
-
"model.visual.blocks.19.norm2.weight": "model-
|
| 549 |
-
"model.visual.blocks.2.attn.proj.bias": "model-
|
| 550 |
-
"model.visual.blocks.2.attn.proj.weight": "model-
|
| 551 |
-
"model.visual.blocks.2.attn.qkv.bias": "model-
|
| 552 |
-
"model.visual.blocks.2.attn.qkv.weight": "model-
|
| 553 |
-
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-
|
| 554 |
-
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-
|
| 555 |
-
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-
|
| 556 |
-
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-
|
| 557 |
-
"model.visual.blocks.2.norm1.bias": "model-
|
| 558 |
-
"model.visual.blocks.2.norm1.weight": "model-
|
| 559 |
-
"model.visual.blocks.2.norm2.bias": "model-
|
| 560 |
-
"model.visual.blocks.2.norm2.weight": "model-
|
| 561 |
-
"model.visual.blocks.20.attn.proj.bias": "model-
|
| 562 |
-
"model.visual.blocks.20.attn.proj.weight": "model-
|
| 563 |
-
"model.visual.blocks.20.attn.qkv.bias": "model-
|
| 564 |
-
"model.visual.blocks.20.attn.qkv.weight": "model-
|
| 565 |
-
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-
|
| 566 |
-
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-
|
| 567 |
-
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-
|
| 568 |
-
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-
|
| 569 |
-
"model.visual.blocks.20.norm1.bias": "model-
|
| 570 |
-
"model.visual.blocks.20.norm1.weight": "model-
|
| 571 |
-
"model.visual.blocks.20.norm2.bias": "model-
|
| 572 |
-
"model.visual.blocks.20.norm2.weight": "model-
|
| 573 |
-
"model.visual.blocks.21.attn.proj.bias": "model-
|
| 574 |
-
"model.visual.blocks.21.attn.proj.weight": "model-
|
| 575 |
-
"model.visual.blocks.21.attn.qkv.bias": "model-
|
| 576 |
-
"model.visual.blocks.21.attn.qkv.weight": "model-
|
| 577 |
-
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-
|
| 578 |
-
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-
|
| 579 |
-
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-
|
| 580 |
-
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-
|
| 581 |
-
"model.visual.blocks.21.norm1.bias": "model-
|
| 582 |
-
"model.visual.blocks.21.norm1.weight": "model-
|
| 583 |
-
"model.visual.blocks.21.norm2.bias": "model-
|
| 584 |
-
"model.visual.blocks.21.norm2.weight": "model-
|
| 585 |
-
"model.visual.blocks.22.attn.proj.bias": "model-
|
| 586 |
-
"model.visual.blocks.22.attn.proj.weight": "model-
|
| 587 |
-
"model.visual.blocks.22.attn.qkv.bias": "model-
|
| 588 |
-
"model.visual.blocks.22.attn.qkv.weight": "model-
|
| 589 |
-
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-
|
| 590 |
-
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-
|
| 591 |
-
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-
|
| 592 |
-
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-
|
| 593 |
-
"model.visual.blocks.22.norm1.bias": "model-
|
| 594 |
-
"model.visual.blocks.22.norm1.weight": "model-
|
| 595 |
-
"model.visual.blocks.22.norm2.bias": "model-
|
| 596 |
-
"model.visual.blocks.22.norm2.weight": "model-
|
| 597 |
-
"model.visual.blocks.23.attn.proj.bias": "model-
|
| 598 |
-
"model.visual.blocks.23.attn.proj.weight": "model-
|
| 599 |
-
"model.visual.blocks.23.attn.qkv.bias": "model-
|
| 600 |
-
"model.visual.blocks.23.attn.qkv.weight": "model-
|
| 601 |
-
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-
|
| 602 |
-
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-
|
| 603 |
-
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-
|
| 604 |
-
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-
|
| 605 |
-
"model.visual.blocks.23.norm1.bias": "model-
|
| 606 |
-
"model.visual.blocks.23.norm1.weight": "model-
|
| 607 |
-
"model.visual.blocks.23.norm2.bias": "model-
|
| 608 |
-
"model.visual.blocks.23.norm2.weight": "model-
|
| 609 |
-
"model.visual.blocks.3.attn.proj.bias": "model-
|
| 610 |
-
"model.visual.blocks.3.attn.proj.weight": "model-
|
| 611 |
-
"model.visual.blocks.3.attn.qkv.bias": "model-
|
| 612 |
-
"model.visual.blocks.3.attn.qkv.weight": "model-
|
| 613 |
-
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-
|
| 614 |
-
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-
|
| 615 |
-
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-
|
| 616 |
-
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-
|
| 617 |
-
"model.visual.blocks.3.norm1.bias": "model-
|
| 618 |
-
"model.visual.blocks.3.norm1.weight": "model-
|
| 619 |
-
"model.visual.blocks.3.norm2.bias": "model-
|
| 620 |
-
"model.visual.blocks.3.norm2.weight": "model-
|
| 621 |
-
"model.visual.blocks.4.attn.proj.bias": "model-
|
| 622 |
-
"model.visual.blocks.4.attn.proj.weight": "model-
|
| 623 |
-
"model.visual.blocks.4.attn.qkv.bias": "model-
|
| 624 |
-
"model.visual.blocks.4.attn.qkv.weight": "model-
|
| 625 |
-
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-
|
| 626 |
-
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-
|
| 627 |
-
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-
|
| 628 |
-
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-
|
| 629 |
-
"model.visual.blocks.4.norm1.bias": "model-
|
| 630 |
-
"model.visual.blocks.4.norm1.weight": "model-
|
| 631 |
-
"model.visual.blocks.4.norm2.bias": "model-
|
| 632 |
-
"model.visual.blocks.4.norm2.weight": "model-
|
| 633 |
-
"model.visual.blocks.5.attn.proj.bias": "model-
|
| 634 |
-
"model.visual.blocks.5.attn.proj.weight": "model-
|
| 635 |
-
"model.visual.blocks.5.attn.qkv.bias": "model-
|
| 636 |
-
"model.visual.blocks.5.attn.qkv.weight": "model-
|
| 637 |
-
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-
|
| 638 |
-
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-
|
| 639 |
-
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-
|
| 640 |
-
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-
|
| 641 |
-
"model.visual.blocks.5.norm1.bias": "model-
|
| 642 |
-
"model.visual.blocks.5.norm1.weight": "model-
|
| 643 |
-
"model.visual.blocks.5.norm2.bias": "model-
|
| 644 |
-
"model.visual.blocks.5.norm2.weight": "model-
|
| 645 |
-
"model.visual.blocks.6.attn.proj.bias": "model-
|
| 646 |
-
"model.visual.blocks.6.attn.proj.weight": "model-
|
| 647 |
-
"model.visual.blocks.6.attn.qkv.bias": "model-
|
| 648 |
-
"model.visual.blocks.6.attn.qkv.weight": "model-
|
| 649 |
-
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-
|
| 650 |
-
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-
|
| 651 |
-
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-
|
| 652 |
-
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-
|
| 653 |
-
"model.visual.blocks.6.norm1.bias": "model-
|
| 654 |
-
"model.visual.blocks.6.norm1.weight": "model-
|
| 655 |
-
"model.visual.blocks.6.norm2.bias": "model-
|
| 656 |
-
"model.visual.blocks.6.norm2.weight": "model-
|
| 657 |
-
"model.visual.blocks.7.attn.proj.bias": "model-
|
| 658 |
-
"model.visual.blocks.7.attn.proj.weight": "model-
|
| 659 |
-
"model.visual.blocks.7.attn.qkv.bias": "model-
|
| 660 |
-
"model.visual.blocks.7.attn.qkv.weight": "model-
|
| 661 |
-
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-
|
| 662 |
-
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-
|
| 663 |
-
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-
|
| 664 |
-
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-
|
| 665 |
-
"model.visual.blocks.7.norm1.bias": "model-
|
| 666 |
-
"model.visual.blocks.7.norm1.weight": "model-
|
| 667 |
-
"model.visual.blocks.7.norm2.bias": "model-
|
| 668 |
-
"model.visual.blocks.7.norm2.weight": "model-
|
| 669 |
-
"model.visual.blocks.8.attn.proj.bias": "model-
|
| 670 |
-
"model.visual.blocks.8.attn.proj.weight": "model-
|
| 671 |
-
"model.visual.blocks.8.attn.qkv.bias": "model-
|
| 672 |
-
"model.visual.blocks.8.attn.qkv.weight": "model-
|
| 673 |
-
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-
|
| 674 |
-
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-
|
| 675 |
-
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-
|
| 676 |
-
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-
|
| 677 |
-
"model.visual.blocks.8.norm1.bias": "model-
|
| 678 |
-
"model.visual.blocks.8.norm1.weight": "model-
|
| 679 |
-
"model.visual.blocks.8.norm2.bias": "model-
|
| 680 |
-
"model.visual.blocks.8.norm2.weight": "model-
|
| 681 |
-
"model.visual.blocks.9.attn.proj.bias": "model-
|
| 682 |
-
"model.visual.blocks.9.attn.proj.weight": "model-
|
| 683 |
-
"model.visual.blocks.9.attn.qkv.bias": "model-
|
| 684 |
-
"model.visual.blocks.9.attn.qkv.weight": "model-
|
| 685 |
-
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-
|
| 686 |
-
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-
|
| 687 |
-
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-
|
| 688 |
-
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-
|
| 689 |
-
"model.visual.blocks.9.norm1.bias": "model-
|
| 690 |
-
"model.visual.blocks.9.norm1.weight": "model-
|
| 691 |
-
"model.visual.blocks.9.norm2.bias": "model-
|
| 692 |
-
"model.visual.blocks.9.norm2.weight": "model-
|
| 693 |
-
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-
|
| 694 |
-
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-
|
| 695 |
-
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-
|
| 696 |
-
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-
|
| 697 |
-
"model.visual.deepstack_merger_list.0.norm.bias": "model-
|
| 698 |
-
"model.visual.deepstack_merger_list.0.norm.weight": "model-
|
| 699 |
-
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-
|
| 700 |
-
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-
|
| 701 |
-
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-
|
| 702 |
-
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-
|
| 703 |
-
"model.visual.deepstack_merger_list.1.norm.bias": "model-
|
| 704 |
-
"model.visual.deepstack_merger_list.1.norm.weight": "model-
|
| 705 |
-
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-
|
| 706 |
-
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-
|
| 707 |
-
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-
|
| 708 |
-
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-
|
| 709 |
-
"model.visual.deepstack_merger_list.2.norm.bias": "model-
|
| 710 |
-
"model.visual.deepstack_merger_list.2.norm.weight": "model-
|
| 711 |
-
"model.visual.merger.linear_fc1.bias": "model-
|
| 712 |
-
"model.visual.merger.linear_fc1.weight": "model-
|
| 713 |
-
"model.visual.merger.linear_fc2.bias": "model-
|
| 714 |
-
"model.visual.merger.linear_fc2.weight": "model-
|
| 715 |
-
"model.visual.merger.norm.bias": "model-
|
| 716 |
-
"model.visual.merger.norm.weight": "model-
|
| 717 |
-
"model.visual.patch_embed.proj.bias": "model-
|
| 718 |
-
"model.visual.patch_embed.proj.weight": "model-
|
| 719 |
-
"model.visual.pos_embed.weight": "model-
|
| 720 |
}
|
| 721 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
|
|
|
| 3 |
"total_size": 8875631616
|
| 4 |
},
|
| 5 |
"weight_map": {
|
|
|
|
| 92 |
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
"model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 100 |
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 101 |
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 140 |
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 147 |
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 148 |
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 151 |
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 162 |
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 401 |
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 404 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 405 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 408 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 409 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 410 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 411 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 412 |
+
"model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
|
| 413 |
+
"model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
|
| 414 |
+
"model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
|
| 415 |
+
"model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
|
| 416 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 417 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 418 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 419 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 420 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 421 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 422 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 423 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 424 |
+
"model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
|
| 425 |
+
"model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
|
| 426 |
+
"model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
|
| 427 |
+
"model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
|
| 428 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 429 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 430 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 431 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 432 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 433 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 434 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 435 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 436 |
+
"model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 441 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 442 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 443 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 444 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 445 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 446 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 447 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 448 |
+
"model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
|
| 449 |
+
"model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
|
| 450 |
+
"model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
|
| 451 |
+
"model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
|
| 452 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 453 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 454 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 455 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 456 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 457 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 458 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 459 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 460 |
+
"model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
|
| 461 |
+
"model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
|
| 462 |
+
"model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
|
| 463 |
+
"model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
|
| 464 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 465 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 466 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 467 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 468 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 469 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 470 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 471 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 472 |
+
"model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
|
| 473 |
+
"model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
|
| 474 |
+
"model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
|
| 475 |
+
"model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
|
| 476 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 477 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 478 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 479 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 480 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 481 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 482 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 483 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 484 |
+
"model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
|
| 485 |
+
"model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
|
| 486 |
+
"model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
|
| 487 |
+
"model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
|
| 488 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 489 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 490 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 491 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 492 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 493 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 494 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 495 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 496 |
+
"model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
|
| 497 |
+
"model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
|
| 498 |
+
"model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
|
| 499 |
+
"model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
|
| 500 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 501 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 502 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 503 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 504 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 505 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 506 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 507 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 508 |
+
"model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
|
| 509 |
+
"model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
|
| 510 |
+
"model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
|
| 511 |
+
"model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
|
| 512 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 513 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 514 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 515 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 516 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 517 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 518 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 519 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 520 |
+
"model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
|
| 521 |
+
"model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
|
| 522 |
+
"model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
|
| 523 |
+
"model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
|
| 524 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 525 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 526 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 527 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 528 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 529 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 530 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 531 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 532 |
+
"model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
|
| 533 |
+
"model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
|
| 534 |
+
"model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
|
| 535 |
+
"model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
|
| 536 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 537 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 538 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 539 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 540 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 541 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 542 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 543 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 544 |
+
"model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
|
| 545 |
+
"model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
|
| 546 |
+
"model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
|
| 547 |
+
"model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
|
| 548 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 549 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 550 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 551 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 552 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 553 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 554 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 555 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 556 |
+
"model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
|
| 557 |
+
"model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
|
| 558 |
+
"model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
|
| 559 |
+
"model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
|
| 560 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 561 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 562 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 563 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 564 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 565 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 566 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 568 |
+
"model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
|
| 569 |
+
"model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
|
| 570 |
+
"model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
|
| 571 |
+
"model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
|
| 572 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 573 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 574 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 575 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 576 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 577 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 578 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 579 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 580 |
+
"model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
|
| 581 |
+
"model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
|
| 582 |
+
"model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
|
| 583 |
+
"model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 585 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 586 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 587 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 588 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 589 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 590 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 591 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 592 |
+
"model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
|
| 593 |
+
"model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
|
| 594 |
+
"model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
|
| 595 |
+
"model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
|
| 596 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 597 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 598 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 599 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 600 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 601 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 602 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 603 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 604 |
+
"model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
|
| 605 |
+
"model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
|
| 606 |
+
"model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
|
| 607 |
+
"model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
|
| 608 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 609 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 610 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 611 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 612 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 613 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 614 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 615 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 616 |
+
"model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
|
| 617 |
+
"model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
|
| 618 |
+
"model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
|
| 619 |
+
"model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
|
| 620 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 621 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 622 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 623 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 624 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 625 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 626 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 627 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 628 |
+
"model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
|
| 629 |
+
"model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
|
| 630 |
+
"model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
|
| 631 |
+
"model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
|
| 632 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 633 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 634 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 635 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 636 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 637 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 638 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 639 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 640 |
+
"model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
|
| 641 |
+
"model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
|
| 642 |
+
"model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
|
| 643 |
+
"model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
|
| 644 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 645 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 646 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 647 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 648 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 652 |
+
"model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
|
| 653 |
+
"model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
|
| 654 |
+
"model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
|
| 655 |
+
"model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
|
| 656 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 657 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 658 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 659 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 660 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 661 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 662 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 663 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 664 |
+
"model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
|
| 665 |
+
"model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
|
| 666 |
+
"model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
|
| 667 |
+
"model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 669 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 670 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 671 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 672 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 673 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 674 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 675 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 676 |
+
"model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
|
| 677 |
+
"model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
|
| 678 |
+
"model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
|
| 679 |
+
"model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
|
| 680 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 681 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 682 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 683 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 684 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 685 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 686 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 687 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 688 |
+
"model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
|
| 689 |
+
"model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
|
| 690 |
+
"model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
|
| 691 |
+
"model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
|
| 692 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 693 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 694 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 695 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 696 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors",
|
| 697 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
|
| 698 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 699 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 701 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 702 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors",
|
| 703 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 705 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 707 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 708 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
|
| 709 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
|
| 710 |
+
"model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 711 |
+
"model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 712 |
+
"model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 713 |
+
"model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 714 |
+
"model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
|
| 715 |
+
"model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
|
| 716 |
+
"model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
|
| 717 |
+
"model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
|
| 718 |
+
"model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
|
| 719 |
}
|
| 720 |
}
|
tokenizer_config.json
CHANGED
|
@@ -238,5 +238,5 @@
|
|
| 238 |
"split_special_tokens": false,
|
| 239 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 240 |
"unk_token": null,
|
| 241 |
-
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count) %}\n {%- if content is string %}\n {{- content }}\n {%- else %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n{%- endmacro %}\n{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- render_content(messages[0].content, false) + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + render_content(messages[0].content, false) + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false) %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, True) %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')
|
| 242 |
}
|
|
|
|
| 238 |
"split_special_tokens": false,
|
| 239 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 240 |
"unk_token": null,
|
| 241 |
+
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count) %}\n {%- if content is string %}\n {{- content }}\n {%- else %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n{%- endmacro %}\n{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- render_content(messages[0].content, false) + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + render_content(messages[0].content, false) + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false) %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, True) %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = ((content.split('</think>')|first).rstrip('\\n').split('<think>')|last).lstrip('\\n') %}\n {%- set content = (content.split('</think>')|last).lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}\n"
|
| 242 |
}
|