Hugging Face's logo

arthurcollet
/
Qwen3-VL-Reranker-2B-mlx

Image-to-Text
Transformers
Safetensors
MLX
qwen3_vl
multimodal rerank
Model card Files
xet
Community
arthurcollet commited on
Commit
5a5bc85
·
verified ·
1 Parent(s): c539c7b

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. README.md +22 -0
  3. added_tokens.json +28 -0
  4. chat_template.jinja +120 -0
  5. config.json +69 -0
  6. generation_config.json +13 -0
  7. model.safetensors +3 -0
  8. model.safetensors.index.json +632 -0
  9. preprocessor_config.json +29 -0
  10. processor_config.json +65 -0
  11. special_tokens_map.json +31 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +31 -0
  14. video_preprocessor_config.json +41 -0
  15. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model:
4
+ - Qwen/Qwen3-VL-2B-Instruct
5
+ tags:
6
+ - transformers
7
+ - multimodal rerank
8
+ - mlx
9
+ ---
10
+
11
+ # arthurcollet/Qwen3-VL-Reranker-2B-mlx
12
+ This model was converted to MLX format from [`Qwen/Qwen3-VL-Reranker-2B`]() using mlx-vlm version **0.3.9**.
13
+ Refer to the [original model card](https://huggingface.co/Qwen/Qwen3-VL-Reranker-2B) for more details on the model.
14
+ ## Use with mlx
15
+
16
+ ```bash
17
+ pip install -U mlx-vlm
18
+ ```
19
+
20
+ ```bash
21
+ python -m mlx_vlm.generate --model arthurcollet/Qwen3-VL-Reranker-2B-mlx --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
22
+ ```
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {%- if messages[0].content is string %}
5
+ {{- messages[0].content }}
6
+ {%- else %}
7
+ {%- for content in messages[0].content %}
8
+ {%- if 'text' in content %}
9
+ {{- content.text }}
10
+ {%- endif %}
11
+ {%- endfor %}
12
+ {%- endif %}
13
+ {{- '\n\n' }}
14
+ {%- endif %}
15
+ {{- "# 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>" }}
16
+ {%- for tool in tools %}
17
+ {{- "\n" }}
18
+ {{- tool | tojson }}
19
+ {%- endfor %}
20
+ {{- "\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" }}
21
+ {%- else %}
22
+ {%- if messages[0].role == 'system' %}
23
+ {{- '<|im_start|>system\n' }}
24
+ {%- if messages[0].content is string %}
25
+ {{- messages[0].content }}
26
+ {%- else %}
27
+ {%- for content in messages[0].content %}
28
+ {%- if 'text' in content %}
29
+ {{- content.text }}
30
+ {%- endif %}
31
+ {%- endfor %}
32
+ {%- endif %}
33
+ {{- '<|im_end|>\n' }}
34
+ {%- endif %}
35
+ {%- endif %}
36
+ {%- set image_count = namespace(value=0) %}
37
+ {%- set video_count = namespace(value=0) %}
38
+ {%- for message in messages %}
39
+ {%- if message.role == "user" %}
40
+ {{- '<|im_start|>' + message.role + '\n' }}
41
+ {%- if message.content is string %}
42
+ {{- message.content }}
43
+ {%- else %}
44
+ {%- for content in message.content %}
45
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
46
+ {%- set image_count.value = image_count.value + 1 %}
47
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
48
+ <|vision_start|><|image_pad|><|vision_end|>
49
+ {%- elif content.type == 'video' or 'video' in content %}
50
+ {%- set video_count.value = video_count.value + 1 %}
51
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
52
+ <|vision_start|><|video_pad|><|vision_end|>
53
+ {%- elif 'text' in content %}
54
+ {{- content.text }}
55
+ {%- endif %}
56
+ {%- endfor %}
57
+ {%- endif %}
58
+ {{- '<|im_end|>\n' }}
59
+ {%- elif message.role == "assistant" %}
60
+ {{- '<|im_start|>' + message.role + '\n' }}
61
+ {%- if message.content is string %}
62
+ {{- message.content }}
63
+ {%- else %}
64
+ {%- for content_item in message.content %}
65
+ {%- if 'text' in content_item %}
66
+ {{- content_item.text }}
67
+ {%- endif %}
68
+ {%- endfor %}
69
+ {%- endif %}
70
+ {%- if message.tool_calls %}
71
+ {%- for tool_call in message.tool_calls %}
72
+ {%- if (loop.first and message.content) or (not loop.first) %}
73
+ {{- '\n' }}
74
+ {%- endif %}
75
+ {%- if tool_call.function %}
76
+ {%- set tool_call = tool_call.function %}
77
+ {%- endif %}
78
+ {{- '<tool_call>\n{"name": "' }}
79
+ {{- tool_call.name }}
80
+ {{- '", "arguments": ' }}
81
+ {%- if tool_call.arguments is string %}
82
+ {{- tool_call.arguments }}
83
+ {%- else %}
84
+ {{- tool_call.arguments | tojson }}
85
+ {%- endif %}
86
+ {{- '}\n</tool_call>' }}
87
+ {%- endfor %}
88
+ {%- endif %}
89
+ {{- '<|im_end|>\n' }}
90
+ {%- elif message.role == "tool" %}
91
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
92
+ {{- '<|im_start|>user' }}
93
+ {%- endif %}
94
+ {{- '\n<tool_response>\n' }}
95
+ {%- if message.content is string %}
96
+ {{- message.content }}
97
+ {%- else %}
98
+ {%- for content in message.content %}
99
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
100
+ {%- set image_count.value = image_count.value + 1 %}
101
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
102
+ <|vision_start|><|image_pad|><|vision_end|>
103
+ {%- elif content.type == 'video' or 'video' in content %}
104
+ {%- set video_count.value = video_count.value + 1 %}
105
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
106
+ <|vision_start|><|video_pad|><|vision_end|>
107
+ {%- elif 'text' in content %}
108
+ {{- content.text }}
109
+ {%- endif %}
110
+ {%- endfor %}
111
+ {%- endif %}
112
+ {{- '\n</tool_response>' }}
113
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
114
+ {{- '<|im_end|>\n' }}
115
+ {%- endif %}
116
+ {%- endif %}
117
+ {%- endfor %}
118
+ {%- if add_generation_prompt %}
119
+ {{- '<|im_start|>assistant\n' }}
120
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "hidden_size": 2048,
7
+ "image_token_id": 151655,
8
+ "model_type": "qwen3_vl",
9
+ "pad_token_id": 151643,
10
+ "text_config": {
11
+ "attention_bias": false,
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 151643,
14
+ "dtype": "float32",
15
+ "eos_token_id": 151645,
16
+ "head_dim": 128,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 2048,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 6144,
21
+ "max_position_embeddings": 262144,
22
+ "model_type": "qwen3_vl_text",
23
+ "num_attention_heads": 16,
24
+ "num_hidden_layers": 28,
25
+ "num_key_value_heads": 8,
26
+ "pad_token_id": 151643,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_scaling": {
29
+ "mrope_interleaved": true,
30
+ "mrope_section": [
31
+ 24,
32
+ 20,
33
+ 20
34
+ ],
35
+ "rope_type": "default"
36
+ },
37
+ "rope_theta": 5000000,
38
+ "tie_word_embeddings": true,
39
+ "use_cache": false,
40
+ "vocab_size": 151936
41
+ },
42
+ "tie_word_embeddings": true,
43
+ "transformers_version": "4.57.0",
44
+ "video_token_id": 151656,
45
+ "vision_config": {
46
+ "deepstack_visual_indexes": [
47
+ 5,
48
+ 11,
49
+ 17
50
+ ],
51
+ "depth": 24,
52
+ "dtype": "float32",
53
+ "hidden_act": "gelu_pytorch_tanh",
54
+ "hidden_size": 1024,
55
+ "in_channels": 3,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 4096,
58
+ "model_type": "qwen3_vl",
59
+ "num_heads": 16,
60
+ "num_position_embeddings": 2304,
61
+ "out_hidden_size": 2048,
62
+ "pad_token_id": 151643,
63
+ "patch_size": 16,
64
+ "spatial_merge_size": 2,
65
+ "temporal_patch_size": 2
66
+ },
67
+ "vision_end_token_id": 151653,
68
+ "vision_start_token_id": 151652
69
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.0"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e086c13e5b3f0b4a8800fa223b7123f59b838b6f185246fe6f2acb20b268438
3
+ size 4255140149
model.safetensors.index.json ADDED
@@ -0,0 +1,632 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 4255064064
4
+ },
5
+ "weight_map": {
6
+ "language_model.model.embed_tokens.weight": "model.safetensors",
7
+ "language_model.model.layers.0.input_layernorm.weight": "model.safetensors",
8
+ "language_model.model.layers.0.mlp.down_proj.weight": "model.safetensors",
9
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
10
+ "language_model.model.layers.0.mlp.up_proj.weight": "model.safetensors",
11
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
12
+ "language_model.model.layers.0.self_attn.k_norm.weight": "model.safetensors",
13
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model.safetensors",
14
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model.safetensors",
15
+ "language_model.model.layers.0.self_attn.q_norm.weight": "model.safetensors",
16
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model.safetensors",
17
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model.safetensors",
18
+ "language_model.model.layers.1.input_layernorm.weight": "model.safetensors",
19
+ "language_model.model.layers.1.mlp.down_proj.weight": "model.safetensors",
20
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model.safetensors",
21
+ "language_model.model.layers.1.mlp.up_proj.weight": "model.safetensors",
22
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
23
+ "language_model.model.layers.1.self_attn.k_norm.weight": "model.safetensors",
24
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model.safetensors",
25
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model.safetensors",
26
+ "language_model.model.layers.1.self_attn.q_norm.weight": "model.safetensors",
27
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model.safetensors",
28
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model.safetensors",
29
+ "language_model.model.layers.10.input_layernorm.weight": "model.safetensors",
30
+ "language_model.model.layers.10.mlp.down_proj.weight": "model.safetensors",
31
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model.safetensors",
32
+ "language_model.model.layers.10.mlp.up_proj.weight": "model.safetensors",
33
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model.safetensors",
34
+ "language_model.model.layers.10.self_attn.k_norm.weight": "model.safetensors",
35
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model.safetensors",
36
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model.safetensors",
37
+ "language_model.model.layers.10.self_attn.q_norm.weight": "model.safetensors",
38
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model.safetensors",
39
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model.safetensors",
40
+ "language_model.model.layers.11.input_layernorm.weight": "model.safetensors",
41
+ "language_model.model.layers.11.mlp.down_proj.weight": "model.safetensors",
42
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model.safetensors",
43
+ "language_model.model.layers.11.mlp.up_proj.weight": "model.safetensors",
44
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model.safetensors",
45
+ "language_model.model.layers.11.self_attn.k_norm.weight": "model.safetensors",
46
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model.safetensors",
47
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model.safetensors",
48
+ "language_model.model.layers.11.self_attn.q_norm.weight": "model.safetensors",
49
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model.safetensors",
50
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model.safetensors",
51
+ "language_model.model.layers.12.input_layernorm.weight": "model.safetensors",
52
+ "language_model.model.layers.12.mlp.down_proj.weight": "model.safetensors",
53
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model.safetensors",
54
+ "language_model.model.layers.12.mlp.up_proj.weight": "model.safetensors",
55
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model.safetensors",
56
+ "language_model.model.layers.12.self_attn.k_norm.weight": "model.safetensors",
57
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model.safetensors",
58
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model.safetensors",
59
+ "language_model.model.layers.12.self_attn.q_norm.weight": "model.safetensors",
60
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model.safetensors",
61
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model.safetensors",
62
+ "language_model.model.layers.13.input_layernorm.weight": "model.safetensors",
63
+ "language_model.model.layers.13.mlp.down_proj.weight": "model.safetensors",
64
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model.safetensors",
65
+ "language_model.model.layers.13.mlp.up_proj.weight": "model.safetensors",
66
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model.safetensors",
67
+ "language_model.model.layers.13.self_attn.k_norm.weight": "model.safetensors",
68
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model.safetensors",
69
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model.safetensors",
70
+ "language_model.model.layers.13.self_attn.q_norm.weight": "model.safetensors",
71
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model.safetensors",
72
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model.safetensors",
73
+ "language_model.model.layers.14.input_layernorm.weight": "model.safetensors",
74
+ "language_model.model.layers.14.mlp.down_proj.weight": "model.safetensors",
75
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model.safetensors",
76
+ "language_model.model.layers.14.mlp.up_proj.weight": "model.safetensors",
77
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model.safetensors",
78
+ "language_model.model.layers.14.self_attn.k_norm.weight": "model.safetensors",
79
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model.safetensors",
80
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model.safetensors",
81
+ "language_model.model.layers.14.self_attn.q_norm.weight": "model.safetensors",
82
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model.safetensors",
83
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model.safetensors",
84
+ "language_model.model.layers.15.input_layernorm.weight": "model.safetensors",
85
+ "language_model.model.layers.15.mlp.down_proj.weight": "model.safetensors",
86
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model.safetensors",
87
+ "language_model.model.layers.15.mlp.up_proj.weight": "model.safetensors",
88
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model.safetensors",
89
+ "language_model.model.layers.15.self_attn.k_norm.weight": "model.safetensors",
90
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model.safetensors",
91
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model.safetensors",
92
+ "language_model.model.layers.15.self_attn.q_norm.weight": "model.safetensors",
93
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model.safetensors",
94
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model.safetensors",
95
+ "language_model.model.layers.16.input_layernorm.weight": "model.safetensors",
96
+ "language_model.model.layers.16.mlp.down_proj.weight": "model.safetensors",
97
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model.safetensors",
98
+ "language_model.model.layers.16.mlp.up_proj.weight": "model.safetensors",
99
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model.safetensors",
100
+ "language_model.model.layers.16.self_attn.k_norm.weight": "model.safetensors",
101
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model.safetensors",
102
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model.safetensors",
103
+ "language_model.model.layers.16.self_attn.q_norm.weight": "model.safetensors",
104
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model.safetensors",
105
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model.safetensors",
106
+ "language_model.model.layers.17.input_layernorm.weight": "model.safetensors",
107
+ "language_model.model.layers.17.mlp.down_proj.weight": "model.safetensors",
108
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model.safetensors",
109
+ "language_model.model.layers.17.mlp.up_proj.weight": "model.safetensors",
110
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model.safetensors",
111
+ "language_model.model.layers.17.self_attn.k_norm.weight": "model.safetensors",
112
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model.safetensors",
113
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model.safetensors",
114
+ "language_model.model.layers.17.self_attn.q_norm.weight": "model.safetensors",
115
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model.safetensors",
116
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model.safetensors",
117
+ "language_model.model.layers.18.input_layernorm.weight": "model.safetensors",
118
+ "language_model.model.layers.18.mlp.down_proj.weight": "model.safetensors",
119
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model.safetensors",
120
+ "language_model.model.layers.18.mlp.up_proj.weight": "model.safetensors",
121
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model.safetensors",
122
+ "language_model.model.layers.18.self_attn.k_norm.weight": "model.safetensors",
123
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model.safetensors",
124
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model.safetensors",
125
+ "language_model.model.layers.18.self_attn.q_norm.weight": "model.safetensors",
126
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model.safetensors",
127
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model.safetensors",
128
+ "language_model.model.layers.19.input_layernorm.weight": "model.safetensors",
129
+ "language_model.model.layers.19.mlp.down_proj.weight": "model.safetensors",
130
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model.safetensors",
131
+ "language_model.model.layers.19.mlp.up_proj.weight": "model.safetensors",
132
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model.safetensors",
133
+ "language_model.model.layers.19.self_attn.k_norm.weight": "model.safetensors",
134
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model.safetensors",
135
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model.safetensors",
136
+ "language_model.model.layers.19.self_attn.q_norm.weight": "model.safetensors",
137
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model.safetensors",
138
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model.safetensors",
139
+ "language_model.model.layers.2.input_layernorm.weight": "model.safetensors",
140
+ "language_model.model.layers.2.mlp.down_proj.weight": "model.safetensors",
141
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model.safetensors",
142
+ "language_model.model.layers.2.mlp.up_proj.weight": "model.safetensors",
143
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
144
+ "language_model.model.layers.2.self_attn.k_norm.weight": "model.safetensors",
145
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model.safetensors",
146
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model.safetensors",
147
+ "language_model.model.layers.2.self_attn.q_norm.weight": "model.safetensors",
148
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model.safetensors",
149
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model.safetensors",
150
+ "language_model.model.layers.20.input_layernorm.weight": "model.safetensors",
151
+ "language_model.model.layers.20.mlp.down_proj.weight": "model.safetensors",
152
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model.safetensors",
153
+ "language_model.model.layers.20.mlp.up_proj.weight": "model.safetensors",
154
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model.safetensors",
155
+ "language_model.model.layers.20.self_attn.k_norm.weight": "model.safetensors",
156
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model.safetensors",
157
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model.safetensors",
158
+ "language_model.model.layers.20.self_attn.q_norm.weight": "model.safetensors",
159
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model.safetensors",
160
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model.safetensors",
161
+ "language_model.model.layers.21.input_layernorm.weight": "model.safetensors",
162
+ "language_model.model.layers.21.mlp.down_proj.weight": "model.safetensors",
163
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model.safetensors",
164
+ "language_model.model.layers.21.mlp.up_proj.weight": "model.safetensors",
165
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model.safetensors",
166
+ "language_model.model.layers.21.self_attn.k_norm.weight": "model.safetensors",
167
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model.safetensors",
168
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model.safetensors",
169
+ "language_model.model.layers.21.self_attn.q_norm.weight": "model.safetensors",
170
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model.safetensors",
171
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model.safetensors",
172
+ "language_model.model.layers.22.input_layernorm.weight": "model.safetensors",
173
+ "language_model.model.layers.22.mlp.down_proj.weight": "model.safetensors",
174
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model.safetensors",
175
+ "language_model.model.layers.22.mlp.up_proj.weight": "model.safetensors",
176
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model.safetensors",
177
+ "language_model.model.layers.22.self_attn.k_norm.weight": "model.safetensors",
178
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model.safetensors",
179
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model.safetensors",
180
+ "language_model.model.layers.22.self_attn.q_norm.weight": "model.safetensors",
181
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model.safetensors",
182
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model.safetensors",
183
+ "language_model.model.layers.23.input_layernorm.weight": "model.safetensors",
184
+ "language_model.model.layers.23.mlp.down_proj.weight": "model.safetensors",
185
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model.safetensors",
186
+ "language_model.model.layers.23.mlp.up_proj.weight": "model.safetensors",
187
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model.safetensors",
188
+ "language_model.model.layers.23.self_attn.k_norm.weight": "model.safetensors",
189
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model.safetensors",
190
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model.safetensors",
191
+ "language_model.model.layers.23.self_attn.q_norm.weight": "model.safetensors",
192
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model.safetensors",
193
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model.safetensors",
194
+ "language_model.model.layers.24.input_layernorm.weight": "model.safetensors",
195
+ "language_model.model.layers.24.mlp.down_proj.weight": "model.safetensors",
196
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model.safetensors",
197
+ "language_model.model.layers.24.mlp.up_proj.weight": "model.safetensors",
198
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model.safetensors",
199
+ "language_model.model.layers.24.self_attn.k_norm.weight": "model.safetensors",
200
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model.safetensors",
201
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model.safetensors",
202
+ "language_model.model.layers.24.self_attn.q_norm.weight": "model.safetensors",
203
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model.safetensors",
204
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model.safetensors",
205
+ "language_model.model.layers.25.input_layernorm.weight": "model.safetensors",
206
+ "language_model.model.layers.25.mlp.down_proj.weight": "model.safetensors",
207
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model.safetensors",
208
+ "language_model.model.layers.25.mlp.up_proj.weight": "model.safetensors",
209
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model.safetensors",
210
+ "language_model.model.layers.25.self_attn.k_norm.weight": "model.safetensors",
211
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model.safetensors",
212
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model.safetensors",
213
+ "language_model.model.layers.25.self_attn.q_norm.weight": "model.safetensors",
214
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model.safetensors",
215
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model.safetensors",
216
+ "language_model.model.layers.26.input_layernorm.weight": "model.safetensors",
217
+ "language_model.model.layers.26.mlp.down_proj.weight": "model.safetensors",
218
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model.safetensors",
219
+ "language_model.model.layers.26.mlp.up_proj.weight": "model.safetensors",
220
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model.safetensors",
221
+ "language_model.model.layers.26.self_attn.k_norm.weight": "model.safetensors",
222
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model.safetensors",
223
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model.safetensors",
224
+ "language_model.model.layers.26.self_attn.q_norm.weight": "model.safetensors",
225
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model.safetensors",
226
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model.safetensors",
227
+ "language_model.model.layers.27.input_layernorm.weight": "model.safetensors",
228
+ "language_model.model.layers.27.mlp.down_proj.weight": "model.safetensors",
229
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model.safetensors",
230
+ "language_model.model.layers.27.mlp.up_proj.weight": "model.safetensors",
231
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model.safetensors",
232
+ "language_model.model.layers.27.self_attn.k_norm.weight": "model.safetensors",
233
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model.safetensors",
234
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model.safetensors",
235
+ "language_model.model.layers.27.self_attn.q_norm.weight": "model.safetensors",
236
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model.safetensors",
237
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model.safetensors",
238
+ "language_model.model.layers.3.input_layernorm.weight": "model.safetensors",
239
+ "language_model.model.layers.3.mlp.down_proj.weight": "model.safetensors",
240
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model.safetensors",
241
+ "language_model.model.layers.3.mlp.up_proj.weight": "model.safetensors",
242
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
243
+ "language_model.model.layers.3.self_attn.k_norm.weight": "model.safetensors",
244
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
245
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
246
+ "language_model.model.layers.3.self_attn.q_norm.weight": "model.safetensors",
247
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
248
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
249
+ "language_model.model.layers.4.input_layernorm.weight": "model.safetensors",
250
+ "language_model.model.layers.4.mlp.down_proj.weight": "model.safetensors",
251
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model.safetensors",
252
+ "language_model.model.layers.4.mlp.up_proj.weight": "model.safetensors",
253
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
254
+ "language_model.model.layers.4.self_attn.k_norm.weight": "model.safetensors",
255
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model.safetensors",
256
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model.safetensors",
257
+ "language_model.model.layers.4.self_attn.q_norm.weight": "model.safetensors",
258
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model.safetensors",
259
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model.safetensors",
260
+ "language_model.model.layers.5.input_layernorm.weight": "model.safetensors",
261
+ "language_model.model.layers.5.mlp.down_proj.weight": "model.safetensors",
262
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model.safetensors",
263
+ "language_model.model.layers.5.mlp.up_proj.weight": "model.safetensors",
264
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model.safetensors",
265
+ "language_model.model.layers.5.self_attn.k_norm.weight": "model.safetensors",
266
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model.safetensors",
267
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model.safetensors",
268
+ "language_model.model.layers.5.self_attn.q_norm.weight": "model.safetensors",
269
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model.safetensors",
270
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model.safetensors",
271
+ "language_model.model.layers.6.input_layernorm.weight": "model.safetensors",
272
+ "language_model.model.layers.6.mlp.down_proj.weight": "model.safetensors",
273
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model.safetensors",
274
+ "language_model.model.layers.6.mlp.up_proj.weight": "model.safetensors",
275
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model.safetensors",
276
+ "language_model.model.layers.6.self_attn.k_norm.weight": "model.safetensors",
277
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model.safetensors",
278
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model.safetensors",
279
+ "language_model.model.layers.6.self_attn.q_norm.weight": "model.safetensors",
280
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model.safetensors",
281
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model.safetensors",
282
+ "language_model.model.layers.7.input_layernorm.weight": "model.safetensors",
283
+ "language_model.model.layers.7.mlp.down_proj.weight": "model.safetensors",
284
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model.safetensors",
285
+ "language_model.model.layers.7.mlp.up_proj.weight": "model.safetensors",
286
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model.safetensors",
287
+ "language_model.model.layers.7.self_attn.k_norm.weight": "model.safetensors",
288
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model.safetensors",
289
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model.safetensors",
290
+ "language_model.model.layers.7.self_attn.q_norm.weight": "model.safetensors",
291
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model.safetensors",
292
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model.safetensors",
293
+ "language_model.model.layers.8.input_layernorm.weight": "model.safetensors",
294
+ "language_model.model.layers.8.mlp.down_proj.weight": "model.safetensors",
295
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model.safetensors",
296
+ "language_model.model.layers.8.mlp.up_proj.weight": "model.safetensors",
297
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model.safetensors",
298
+ "language_model.model.layers.8.self_attn.k_norm.weight": "model.safetensors",
299
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model.safetensors",
300
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model.safetensors",
301
+ "language_model.model.layers.8.self_attn.q_norm.weight": "model.safetensors",
302
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model.safetensors",
303
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model.safetensors",
304
+ "language_model.model.layers.9.input_layernorm.weight": "model.safetensors",
305
+ "language_model.model.layers.9.mlp.down_proj.weight": "model.safetensors",
306
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model.safetensors",
307
+ "language_model.model.layers.9.mlp.up_proj.weight": "model.safetensors",
308
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model.safetensors",
309
+ "language_model.model.layers.9.self_attn.k_norm.weight": "model.safetensors",
310
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model.safetensors",
311
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model.safetensors",
312
+ "language_model.model.layers.9.self_attn.q_norm.weight": "model.safetensors",
313
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model.safetensors",
314
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model.safetensors",
315
+ "language_model.model.norm.weight": "model.safetensors",
316
+ "vision_tower.blocks.0.attn.proj.bias": "model.safetensors",
317
+ "vision_tower.blocks.0.attn.proj.weight": "model.safetensors",
318
+ "vision_tower.blocks.0.attn.qkv.bias": "model.safetensors",
319
+ "vision_tower.blocks.0.attn.qkv.weight": "model.safetensors",
320
+ "vision_tower.blocks.0.mlp.linear_fc1.bias": "model.safetensors",
321
+ "vision_tower.blocks.0.mlp.linear_fc1.weight": "model.safetensors",
322
+ "vision_tower.blocks.0.mlp.linear_fc2.bias": "model.safetensors",
323
+ "vision_tower.blocks.0.mlp.linear_fc2.weight": "model.safetensors",
324
+ "vision_tower.blocks.0.norm1.bias": "model.safetensors",
325
+ "vision_tower.blocks.0.norm1.weight": "model.safetensors",
326
+ "vision_tower.blocks.0.norm2.bias": "model.safetensors",
327
+ "vision_tower.blocks.0.norm2.weight": "model.safetensors",
328
+ "vision_tower.blocks.1.attn.proj.bias": "model.safetensors",
329
+ "vision_tower.blocks.1.attn.proj.weight": "model.safetensors",
330
+ "vision_tower.blocks.1.attn.qkv.bias": "model.safetensors",
331
+ "vision_tower.blocks.1.attn.qkv.weight": "model.safetensors",
332
+ "vision_tower.blocks.1.mlp.linear_fc1.bias": "model.safetensors",
333
+ "vision_tower.blocks.1.mlp.linear_fc1.weight": "model.safetensors",
334
+ "vision_tower.blocks.1.mlp.linear_fc2.bias": "model.safetensors",
335
+ "vision_tower.blocks.1.mlp.linear_fc2.weight": "model.safetensors",
336
+ "vision_tower.blocks.1.norm1.bias": "model.safetensors",
337
+ "vision_tower.blocks.1.norm1.weight": "model.safetensors",
338
+ "vision_tower.blocks.1.norm2.bias": "model.safetensors",
339
+ "vision_tower.blocks.1.norm2.weight": "model.safetensors",
340
+ "vision_tower.blocks.10.attn.proj.bias": "model.safetensors",
341
+ "vision_tower.blocks.10.attn.proj.weight": "model.safetensors",
342
+ "vision_tower.blocks.10.attn.qkv.bias": "model.safetensors",
343
+ "vision_tower.blocks.10.attn.qkv.weight": "model.safetensors",
344
+ "vision_tower.blocks.10.mlp.linear_fc1.bias": "model.safetensors",
345
+ "vision_tower.blocks.10.mlp.linear_fc1.weight": "model.safetensors",
346
+ "vision_tower.blocks.10.mlp.linear_fc2.bias": "model.safetensors",
347
+ "vision_tower.blocks.10.mlp.linear_fc2.weight": "model.safetensors",
348
+ "vision_tower.blocks.10.norm1.bias": "model.safetensors",
349
+ "vision_tower.blocks.10.norm1.weight": "model.safetensors",
350
+ "vision_tower.blocks.10.norm2.bias": "model.safetensors",
351
+ "vision_tower.blocks.10.norm2.weight": "model.safetensors",
352
+ "vision_tower.blocks.11.attn.proj.bias": "model.safetensors",
353
+ "vision_tower.blocks.11.attn.proj.weight": "model.safetensors",
354
+ "vision_tower.blocks.11.attn.qkv.bias": "model.safetensors",
355
+ "vision_tower.blocks.11.attn.qkv.weight": "model.safetensors",
356
+ "vision_tower.blocks.11.mlp.linear_fc1.bias": "model.safetensors",
357
+ "vision_tower.blocks.11.mlp.linear_fc1.weight": "model.safetensors",
358
+ "vision_tower.blocks.11.mlp.linear_fc2.bias": "model.safetensors",
359
+ "vision_tower.blocks.11.mlp.linear_fc2.weight": "model.safetensors",
360
+ "vision_tower.blocks.11.norm1.bias": "model.safetensors",
361
+ "vision_tower.blocks.11.norm1.weight": "model.safetensors",
362
+ "vision_tower.blocks.11.norm2.bias": "model.safetensors",
363
+ "vision_tower.blocks.11.norm2.weight": "model.safetensors",
364
+ "vision_tower.blocks.12.attn.proj.bias": "model.safetensors",
365
+ "vision_tower.blocks.12.attn.proj.weight": "model.safetensors",
366
+ "vision_tower.blocks.12.attn.qkv.bias": "model.safetensors",
367
+ "vision_tower.blocks.12.attn.qkv.weight": "model.safetensors",
368
+ "vision_tower.blocks.12.mlp.linear_fc1.bias": "model.safetensors",
369
+ "vision_tower.blocks.12.mlp.linear_fc1.weight": "model.safetensors",
370
+ "vision_tower.blocks.12.mlp.linear_fc2.bias": "model.safetensors",
371
+ "vision_tower.blocks.12.mlp.linear_fc2.weight": "model.safetensors",
372
+ "vision_tower.blocks.12.norm1.bias": "model.safetensors",
373
+ "vision_tower.blocks.12.norm1.weight": "model.safetensors",
374
+ "vision_tower.blocks.12.norm2.bias": "model.safetensors",
375
+ "vision_tower.blocks.12.norm2.weight": "model.safetensors",
376
+ "vision_tower.blocks.13.attn.proj.bias": "model.safetensors",
377
+ "vision_tower.blocks.13.attn.proj.weight": "model.safetensors",
378
+ "vision_tower.blocks.13.attn.qkv.bias": "model.safetensors",
379
+ "vision_tower.blocks.13.attn.qkv.weight": "model.safetensors",
380
+ "vision_tower.blocks.13.mlp.linear_fc1.bias": "model.safetensors",
381
+ "vision_tower.blocks.13.mlp.linear_fc1.weight": "model.safetensors",
382
+ "vision_tower.blocks.13.mlp.linear_fc2.bias": "model.safetensors",
383
+ "vision_tower.blocks.13.mlp.linear_fc2.weight": "model.safetensors",
384
+ "vision_tower.blocks.13.norm1.bias": "model.safetensors",
385
+ "vision_tower.blocks.13.norm1.weight": "model.safetensors",
386
+ "vision_tower.blocks.13.norm2.bias": "model.safetensors",
387
+ "vision_tower.blocks.13.norm2.weight": "model.safetensors",
388
+ "vision_tower.blocks.14.attn.proj.bias": "model.safetensors",
389
+ "vision_tower.blocks.14.attn.proj.weight": "model.safetensors",
390
+ "vision_tower.blocks.14.attn.qkv.bias": "model.safetensors",
391
+ "vision_tower.blocks.14.attn.qkv.weight": "model.safetensors",
392
+ "vision_tower.blocks.14.mlp.linear_fc1.bias": "model.safetensors",
393
+ "vision_tower.blocks.14.mlp.linear_fc1.weight": "model.safetensors",
394
+ "vision_tower.blocks.14.mlp.linear_fc2.bias": "model.safetensors",
395
+ "vision_tower.blocks.14.mlp.linear_fc2.weight": "model.safetensors",
396
+ "vision_tower.blocks.14.norm1.bias": "model.safetensors",
397
+ "vision_tower.blocks.14.norm1.weight": "model.safetensors",
398
+ "vision_tower.blocks.14.norm2.bias": "model.safetensors",
399
+ "vision_tower.blocks.14.norm2.weight": "model.safetensors",
400
+ "vision_tower.blocks.15.attn.proj.bias": "model.safetensors",
401
+ "vision_tower.blocks.15.attn.proj.weight": "model.safetensors",
402
+ "vision_tower.blocks.15.attn.qkv.bias": "model.safetensors",
403
+ "vision_tower.blocks.15.attn.qkv.weight": "model.safetensors",
404
+ "vision_tower.blocks.15.mlp.linear_fc1.bias": "model.safetensors",
405
+ "vision_tower.blocks.15.mlp.linear_fc1.weight": "model.safetensors",
406
+ "vision_tower.blocks.15.mlp.linear_fc2.bias": "model.safetensors",
407
+ "vision_tower.blocks.15.mlp.linear_fc2.weight": "model.safetensors",
408
+ "vision_tower.blocks.15.norm1.bias": "model.safetensors",
409
+ "vision_tower.blocks.15.norm1.weight": "model.safetensors",
410
+ "vision_tower.blocks.15.norm2.bias": "model.safetensors",
411
+ "vision_tower.blocks.15.norm2.weight": "model.safetensors",
412
+ "vision_tower.blocks.16.attn.proj.bias": "model.safetensors",
413
+ "vision_tower.blocks.16.attn.proj.weight": "model.safetensors",
414
+ "vision_tower.blocks.16.attn.qkv.bias": "model.safetensors",
415
+ "vision_tower.blocks.16.attn.qkv.weight": "model.safetensors",
416
+ "vision_tower.blocks.16.mlp.linear_fc1.bias": "model.safetensors",
417
+ "vision_tower.blocks.16.mlp.linear_fc1.weight": "model.safetensors",
418
+ "vision_tower.blocks.16.mlp.linear_fc2.bias": "model.safetensors",
419
+ "vision_tower.blocks.16.mlp.linear_fc2.weight": "model.safetensors",
420
+ "vision_tower.blocks.16.norm1.bias": "model.safetensors",
421
+ "vision_tower.blocks.16.norm1.weight": "model.safetensors",
422
+ "vision_tower.blocks.16.norm2.bias": "model.safetensors",
423
+ "vision_tower.blocks.16.norm2.weight": "model.safetensors",
424
+ "vision_tower.blocks.17.attn.proj.bias": "model.safetensors",
425
+ "vision_tower.blocks.17.attn.proj.weight": "model.safetensors",
426
+ "vision_tower.blocks.17.attn.qkv.bias": "model.safetensors",
427
+ "vision_tower.blocks.17.attn.qkv.weight": "model.safetensors",
428
+ "vision_tower.blocks.17.mlp.linear_fc1.bias": "model.safetensors",
429
+ "vision_tower.blocks.17.mlp.linear_fc1.weight": "model.safetensors",
430
+ "vision_tower.blocks.17.mlp.linear_fc2.bias": "model.safetensors",
431
+ "vision_tower.blocks.17.mlp.linear_fc2.weight": "model.safetensors",
432
+ "vision_tower.blocks.17.norm1.bias": "model.safetensors",
433
+ "vision_tower.blocks.17.norm1.weight": "model.safetensors",
434
+ "vision_tower.blocks.17.norm2.bias": "model.safetensors",
435
+ "vision_tower.blocks.17.norm2.weight": "model.safetensors",
436
+ "vision_tower.blocks.18.attn.proj.bias": "model.safetensors",
437
+ "vision_tower.blocks.18.attn.proj.weight": "model.safetensors",
438
+ "vision_tower.blocks.18.attn.qkv.bias": "model.safetensors",
439
+ "vision_tower.blocks.18.attn.qkv.weight": "model.safetensors",
440
+ "vision_tower.blocks.18.mlp.linear_fc1.bias": "model.safetensors",
441
+ "vision_tower.blocks.18.mlp.linear_fc1.weight": "model.safetensors",
442
+ "vision_tower.blocks.18.mlp.linear_fc2.bias": "model.safetensors",
443
+ "vision_tower.blocks.18.mlp.linear_fc2.weight": "model.safetensors",
444
+ "vision_tower.blocks.18.norm1.bias": "model.safetensors",
445
+ "vision_tower.blocks.18.norm1.weight": "model.safetensors",
446
+ "vision_tower.blocks.18.norm2.bias": "model.safetensors",
447
+ "vision_tower.blocks.18.norm2.weight": "model.safetensors",
448
+ "vision_tower.blocks.19.attn.proj.bias": "model.safetensors",
449
+ "vision_tower.blocks.19.attn.proj.weight": "model.safetensors",
450
+ "vision_tower.blocks.19.attn.qkv.bias": "model.safetensors",
451
+ "vision_tower.blocks.19.attn.qkv.weight": "model.safetensors",
452
+ "vision_tower.blocks.19.mlp.linear_fc1.bias": "model.safetensors",
453
+ "vision_tower.blocks.19.mlp.linear_fc1.weight": "model.safetensors",
454
+ "vision_tower.blocks.19.mlp.linear_fc2.bias": "model.safetensors",
455
+ "vision_tower.blocks.19.mlp.linear_fc2.weight": "model.safetensors",
456
+ "vision_tower.blocks.19.norm1.bias": "model.safetensors",
457
+ "vision_tower.blocks.19.norm1.weight": "model.safetensors",
458
+ "vision_tower.blocks.19.norm2.bias": "model.safetensors",
459
+ "vision_tower.blocks.19.norm2.weight": "model.safetensors",
460
+ "vision_tower.blocks.2.attn.proj.bias": "model.safetensors",
461
+ "vision_tower.blocks.2.attn.proj.weight": "model.safetensors",
462
+ "vision_tower.blocks.2.attn.qkv.bias": "model.safetensors",
463
+ "vision_tower.blocks.2.attn.qkv.weight": "model.safetensors",
464
+ "vision_tower.blocks.2.mlp.linear_fc1.bias": "model.safetensors",
465
+ "vision_tower.blocks.2.mlp.linear_fc1.weight": "model.safetensors",
466
+ "vision_tower.blocks.2.mlp.linear_fc2.bias": "model.safetensors",
467
+ "vision_tower.blocks.2.mlp.linear_fc2.weight": "model.safetensors",
468
+ "vision_tower.blocks.2.norm1.bias": "model.safetensors",
469
+ "vision_tower.blocks.2.norm1.weight": "model.safetensors",
470
+ "vision_tower.blocks.2.norm2.bias": "model.safetensors",
471
+ "vision_tower.blocks.2.norm2.weight": "model.safetensors",
472
+ "vision_tower.blocks.20.attn.proj.bias": "model.safetensors",
473
+ "vision_tower.blocks.20.attn.proj.weight": "model.safetensors",
474
+ "vision_tower.blocks.20.attn.qkv.bias": "model.safetensors",
475
+ "vision_tower.blocks.20.attn.qkv.weight": "model.safetensors",
476
+ "vision_tower.blocks.20.mlp.linear_fc1.bias": "model.safetensors",
477
+ "vision_tower.blocks.20.mlp.linear_fc1.weight": "model.safetensors",
478
+ "vision_tower.blocks.20.mlp.linear_fc2.bias": "model.safetensors",
479
+ "vision_tower.blocks.20.mlp.linear_fc2.weight": "model.safetensors",
480
+ "vision_tower.blocks.20.norm1.bias": "model.safetensors",
481
+ "vision_tower.blocks.20.norm1.weight": "model.safetensors",
482
+ "vision_tower.blocks.20.norm2.bias": "model.safetensors",
483
+ "vision_tower.blocks.20.norm2.weight": "model.safetensors",
484
+ "vision_tower.blocks.21.attn.proj.bias": "model.safetensors",
485
+ "vision_tower.blocks.21.attn.proj.weight": "model.safetensors",
486
+ "vision_tower.blocks.21.attn.qkv.bias": "model.safetensors",
487
+ "vision_tower.blocks.21.attn.qkv.weight": "model.safetensors",
488
+ "vision_tower.blocks.21.mlp.linear_fc1.bias": "model.safetensors",
489
+ "vision_tower.blocks.21.mlp.linear_fc1.weight": "model.safetensors",
490
+ "vision_tower.blocks.21.mlp.linear_fc2.bias": "model.safetensors",
491
+ "vision_tower.blocks.21.mlp.linear_fc2.weight": "model.safetensors",
492
+ "vision_tower.blocks.21.norm1.bias": "model.safetensors",
493
+ "vision_tower.blocks.21.norm1.weight": "model.safetensors",
494
+ "vision_tower.blocks.21.norm2.bias": "model.safetensors",
495
+ "vision_tower.blocks.21.norm2.weight": "model.safetensors",
496
+ "vision_tower.blocks.22.attn.proj.bias": "model.safetensors",
497
+ "vision_tower.blocks.22.attn.proj.weight": "model.safetensors",
498
+ "vision_tower.blocks.22.attn.qkv.bias": "model.safetensors",
499
+ "vision_tower.blocks.22.attn.qkv.weight": "model.safetensors",
500
+ "vision_tower.blocks.22.mlp.linear_fc1.bias": "model.safetensors",
501
+ "vision_tower.blocks.22.mlp.linear_fc1.weight": "model.safetensors",
502
+ "vision_tower.blocks.22.mlp.linear_fc2.bias": "model.safetensors",
503
+ "vision_tower.blocks.22.mlp.linear_fc2.weight": "model.safetensors",
504
+ "vision_tower.blocks.22.norm1.bias": "model.safetensors",
505
+ "vision_tower.blocks.22.norm1.weight": "model.safetensors",
506
+ "vision_tower.blocks.22.norm2.bias": "model.safetensors",
507
+ "vision_tower.blocks.22.norm2.weight": "model.safetensors",
508
+ "vision_tower.blocks.23.attn.proj.bias": "model.safetensors",
509
+ "vision_tower.blocks.23.attn.proj.weight": "model.safetensors",
510
+ "vision_tower.blocks.23.attn.qkv.bias": "model.safetensors",
511
+ "vision_tower.blocks.23.attn.qkv.weight": "model.safetensors",
512
+ "vision_tower.blocks.23.mlp.linear_fc1.bias": "model.safetensors",
513
+ "vision_tower.blocks.23.mlp.linear_fc1.weight": "model.safetensors",
514
+ "vision_tower.blocks.23.mlp.linear_fc2.bias": "model.safetensors",
515
+ "vision_tower.blocks.23.mlp.linear_fc2.weight": "model.safetensors",
516
+ "vision_tower.blocks.23.norm1.bias": "model.safetensors",
517
+ "vision_tower.blocks.23.norm1.weight": "model.safetensors",
518
+ "vision_tower.blocks.23.norm2.bias": "model.safetensors",
519
+ "vision_tower.blocks.23.norm2.weight": "model.safetensors",
520
+ "vision_tower.blocks.3.attn.proj.bias": "model.safetensors",
521
+ "vision_tower.blocks.3.attn.proj.weight": "model.safetensors",
522
+ "vision_tower.blocks.3.attn.qkv.bias": "model.safetensors",
523
+ "vision_tower.blocks.3.attn.qkv.weight": "model.safetensors",
524
+ "vision_tower.blocks.3.mlp.linear_fc1.bias": "model.safetensors",
525
+ "vision_tower.blocks.3.mlp.linear_fc1.weight": "model.safetensors",
526
+ "vision_tower.blocks.3.mlp.linear_fc2.bias": "model.safetensors",
527
+ "vision_tower.blocks.3.mlp.linear_fc2.weight": "model.safetensors",
528
+ "vision_tower.blocks.3.norm1.bias": "model.safetensors",
529
+ "vision_tower.blocks.3.norm1.weight": "model.safetensors",
530
+ "vision_tower.blocks.3.norm2.bias": "model.safetensors",
531
+ "vision_tower.blocks.3.norm2.weight": "model.safetensors",
532
+ "vision_tower.blocks.4.attn.proj.bias": "model.safetensors",
533
+ "vision_tower.blocks.4.attn.proj.weight": "model.safetensors",
534
+ "vision_tower.blocks.4.attn.qkv.bias": "model.safetensors",
535
+ "vision_tower.blocks.4.attn.qkv.weight": "model.safetensors",
536
+ "vision_tower.blocks.4.mlp.linear_fc1.bias": "model.safetensors",
537
+ "vision_tower.blocks.4.mlp.linear_fc1.weight": "model.safetensors",
538
+ "vision_tower.blocks.4.mlp.linear_fc2.bias": "model.safetensors",
539
+ "vision_tower.blocks.4.mlp.linear_fc2.weight": "model.safetensors",
540
+ "vision_tower.blocks.4.norm1.bias": "model.safetensors",
541
+ "vision_tower.blocks.4.norm1.weight": "model.safetensors",
542
+ "vision_tower.blocks.4.norm2.bias": "model.safetensors",
543
+ "vision_tower.blocks.4.norm2.weight": "model.safetensors",
544
+ "vision_tower.blocks.5.attn.proj.bias": "model.safetensors",
545
+ "vision_tower.blocks.5.attn.proj.weight": "model.safetensors",
546
+ "vision_tower.blocks.5.attn.qkv.bias": "model.safetensors",
547
+ "vision_tower.blocks.5.attn.qkv.weight": "model.safetensors",
548
+ "vision_tower.blocks.5.mlp.linear_fc1.bias": "model.safetensors",
549
+ "vision_tower.blocks.5.mlp.linear_fc1.weight": "model.safetensors",
550
+ "vision_tower.blocks.5.mlp.linear_fc2.bias": "model.safetensors",
551
+ "vision_tower.blocks.5.mlp.linear_fc2.weight": "model.safetensors",
552
+ "vision_tower.blocks.5.norm1.bias": "model.safetensors",
553
+ "vision_tower.blocks.5.norm1.weight": "model.safetensors",
554
+ "vision_tower.blocks.5.norm2.bias": "model.safetensors",
555
+ "vision_tower.blocks.5.norm2.weight": "model.safetensors",
556
+ "vision_tower.blocks.6.attn.proj.bias": "model.safetensors",
557
+ "vision_tower.blocks.6.attn.proj.weight": "model.safetensors",
558
+ "vision_tower.blocks.6.attn.qkv.bias": "model.safetensors",
559
+ "vision_tower.blocks.6.attn.qkv.weight": "model.safetensors",
560
+ "vision_tower.blocks.6.mlp.linear_fc1.bias": "model.safetensors",
561
+ "vision_tower.blocks.6.mlp.linear_fc1.weight": "model.safetensors",
562
+ "vision_tower.blocks.6.mlp.linear_fc2.bias": "model.safetensors",
563
+ "vision_tower.blocks.6.mlp.linear_fc2.weight": "model.safetensors",
564
+ "vision_tower.blocks.6.norm1.bias": "model.safetensors",
565
+ "vision_tower.blocks.6.norm1.weight": "model.safetensors",
566
+ "vision_tower.blocks.6.norm2.bias": "model.safetensors",
567
+ "vision_tower.blocks.6.norm2.weight": "model.safetensors",
568
+ "vision_tower.blocks.7.attn.proj.bias": "model.safetensors",
569
+ "vision_tower.blocks.7.attn.proj.weight": "model.safetensors",
570
+ "vision_tower.blocks.7.attn.qkv.bias": "model.safetensors",
571
+ "vision_tower.blocks.7.attn.qkv.weight": "model.safetensors",
572
+ "vision_tower.blocks.7.mlp.linear_fc1.bias": "model.safetensors",
573
+ "vision_tower.blocks.7.mlp.linear_fc1.weight": "model.safetensors",
574
+ "vision_tower.blocks.7.mlp.linear_fc2.bias": "model.safetensors",
575
+ "vision_tower.blocks.7.mlp.linear_fc2.weight": "model.safetensors",
576
+ "vision_tower.blocks.7.norm1.bias": "model.safetensors",
577
+ "vision_tower.blocks.7.norm1.weight": "model.safetensors",
578
+ "vision_tower.blocks.7.norm2.bias": "model.safetensors",
579
+ "vision_tower.blocks.7.norm2.weight": "model.safetensors",
580
+ "vision_tower.blocks.8.attn.proj.bias": "model.safetensors",
581
+ "vision_tower.blocks.8.attn.proj.weight": "model.safetensors",
582
+ "vision_tower.blocks.8.attn.qkv.bias": "model.safetensors",
583
+ "vision_tower.blocks.8.attn.qkv.weight": "model.safetensors",
584
+ "vision_tower.blocks.8.mlp.linear_fc1.bias": "model.safetensors",
585
+ "vision_tower.blocks.8.mlp.linear_fc1.weight": "model.safetensors",
586
+ "vision_tower.blocks.8.mlp.linear_fc2.bias": "model.safetensors",
587
+ "vision_tower.blocks.8.mlp.linear_fc2.weight": "model.safetensors",
588
+ "vision_tower.blocks.8.norm1.bias": "model.safetensors",
589
+ "vision_tower.blocks.8.norm1.weight": "model.safetensors",
590
+ "vision_tower.blocks.8.norm2.bias": "model.safetensors",
591
+ "vision_tower.blocks.8.norm2.weight": "model.safetensors",
592
+ "vision_tower.blocks.9.attn.proj.bias": "model.safetensors",
593
+ "vision_tower.blocks.9.attn.proj.weight": "model.safetensors",
594
+ "vision_tower.blocks.9.attn.qkv.bias": "model.safetensors",
595
+ "vision_tower.blocks.9.attn.qkv.weight": "model.safetensors",
596
+ "vision_tower.blocks.9.mlp.linear_fc1.bias": "model.safetensors",
597
+ "vision_tower.blocks.9.mlp.linear_fc1.weight": "model.safetensors",
598
+ "vision_tower.blocks.9.mlp.linear_fc2.bias": "model.safetensors",
599
+ "vision_tower.blocks.9.mlp.linear_fc2.weight": "model.safetensors",
600
+ "vision_tower.blocks.9.norm1.bias": "model.safetensors",
601
+ "vision_tower.blocks.9.norm1.weight": "model.safetensors",
602
+ "vision_tower.blocks.9.norm2.bias": "model.safetensors",
603
+ "vision_tower.blocks.9.norm2.weight": "model.safetensors",
604
+ "vision_tower.deepstack_merger_list.0.linear_fc1.bias": "model.safetensors",
605
+ "vision_tower.deepstack_merger_list.0.linear_fc1.weight": "model.safetensors",
606
+ "vision_tower.deepstack_merger_list.0.linear_fc2.bias": "model.safetensors",
607
+ "vision_tower.deepstack_merger_list.0.linear_fc2.weight": "model.safetensors",
608
+ "vision_tower.deepstack_merger_list.0.norm.bias": "model.safetensors",
609
+ "vision_tower.deepstack_merger_list.0.norm.weight": "model.safetensors",
610
+ "vision_tower.deepstack_merger_list.1.linear_fc1.bias": "model.safetensors",
611
+ "vision_tower.deepstack_merger_list.1.linear_fc1.weight": "model.safetensors",
612
+ "vision_tower.deepstack_merger_list.1.linear_fc2.bias": "model.safetensors",
613
+ "vision_tower.deepstack_merger_list.1.linear_fc2.weight": "model.safetensors",
614
+ "vision_tower.deepstack_merger_list.1.norm.bias": "model.safetensors",
615
+ "vision_tower.deepstack_merger_list.1.norm.weight": "model.safetensors",
616
+ "vision_tower.deepstack_merger_list.2.linear_fc1.bias": "model.safetensors",
617
+ "vision_tower.deepstack_merger_list.2.linear_fc1.weight": "model.safetensors",
618
+ "vision_tower.deepstack_merger_list.2.linear_fc2.bias": "model.safetensors",
619
+ "vision_tower.deepstack_merger_list.2.linear_fc2.weight": "model.safetensors",
620
+ "vision_tower.deepstack_merger_list.2.norm.bias": "model.safetensors",
621
+ "vision_tower.deepstack_merger_list.2.norm.weight": "model.safetensors",
622
+ "vision_tower.merger.linear_fc1.bias": "model.safetensors",
623
+ "vision_tower.merger.linear_fc1.weight": "model.safetensors",
624
+ "vision_tower.merger.linear_fc2.bias": "model.safetensors",
625
+ "vision_tower.merger.linear_fc2.weight": "model.safetensors",
626
+ "vision_tower.merger.norm.bias": "model.safetensors",
627
+ "vision_tower.merger.norm.weight": "model.safetensors",
628
+ "vision_tower.patch_embed.proj.bias": "model.safetensors",
629
+ "vision_tower.patch_embed.proj.weight": "model.safetensors",
630
+ "vision_tower.pos_embed.weight": "model.safetensors"
631
+ }
632
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "processor_class": "Qwen3VLProcessor",
19
+ "image_processor_type": "Qwen2VLImageProcessorFast",
20
+ "input_data_format": null,
21
+ "max_pixels": 1310720,
22
+ "merge_size": 2,
23
+ "min_pixels": 4095,
24
+ "pad_size": null,
25
+ "processor_class": "Qwen3VLProcessor",
26
+ "resample": 3,
27
+ "rescale_factor": 0.00392156862745098,
28
+ "return_tensors": null
29
+ }
processor_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Qwen2VLImageProcessorFast",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "max_pixels": 1310720,
20
+ "merge_size": 2,
21
+ "min_pixels": 4095,
22
+ "patch_size": 16,
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "longest_edge": 1310720,
27
+ "shortest_edge": 4095
28
+ },
29
+ "temporal_patch_size": 2
30
+ },
31
+ "processor_class": "Qwen3VLProcessor",
32
+ "video_processor": {
33
+ "data_format": "channels_first",
34
+ "default_to_square": true,
35
+ "do_convert_rgb": true,
36
+ "do_normalize": true,
37
+ "do_rescale": true,
38
+ "do_resize": true,
39
+ "do_sample_frames": true,
40
+ "fps": 2,
41
+ "image_mean": [
42
+ 0.5,
43
+ 0.5,
44
+ 0.5
45
+ ],
46
+ "image_std": [
47
+ 0.5,
48
+ 0.5,
49
+ 0.5
50
+ ],
51
+ "max_frames": 768,
52
+ "merge_size": 2,
53
+ "min_frames": 4,
54
+ "patch_size": 16,
55
+ "resample": 3,
56
+ "rescale_factor": 0.00392156862745098,
57
+ "return_metadata": false,
58
+ "size": {
59
+ "longest_edge": 25165824,
60
+ "shortest_edge": 4096
61
+ },
62
+ "temporal_patch_size": 2,
63
+ "video_processor_type": "Qwen3VLVideoProcessor"
64
+ }
65
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": true,
24
+ "model_max_length": 262144,
25
+ "model_specific_special_tokens": {},
26
+ "pad_token": "<|endoftext|>",
27
+ "processor_class": "Qwen3VLProcessor",
28
+ "split_special_tokens": false,
29
+ "tokenizer_class": "Qwen2Tokenizer",
30
+ "unk_token": null
31
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "do_sample_frames": true,
12
+ "fps": 2,
13
+ "image_mean": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "image_std": [
19
+ 0.5,
20
+ 0.5,
21
+ 0.5
22
+ ],
23
+ "input_data_format": null,
24
+ "max_frames": 768,
25
+ "merge_size": 2,
26
+ "min_frames": 4,
27
+ "num_frames": null,
28
+ "pad_size": null,
29
+ "patch_size": 16,
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_metadata": false,
34
+ "size": {
35
+ "longest_edge": 25165824,
36
+ "shortest_edge": 4096
37
+ },
38
+ "temporal_patch_size": 2,
39
+ "video_metadata": null,
40
+ "video_processor_type": "Qwen3VLVideoProcessor"
41
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff