Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- chat_template.jinja +7 -0
- config.json +542 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +29 -0
- quantization_config.json +408 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +208 -0
- video_preprocessor_config.json +43 -0
- 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
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
chat_template.jinja
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
|
2 |
+
You are a helpful assistant.<|im_end|>
|
3 |
+
{% endif %}<|im_start|>{{ message['role'] }}
|
4 |
+
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
|
5 |
+
{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
|
6 |
+
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
7 |
+
{% endif %}
|
config.json
ADDED
@@ -0,0 +1,542 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 151643,
|
7 |
+
"eos_token_id": 151645,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 3584,
|
10 |
+
"image_token_id": 151655,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 18944,
|
13 |
+
"max_position_embeddings": 128000,
|
14 |
+
"max_window_layers": 28,
|
15 |
+
"model_type": "qwen2_5_vl",
|
16 |
+
"num_attention_heads": 28,
|
17 |
+
"num_hidden_layers": 28,
|
18 |
+
"num_key_value_heads": 4,
|
19 |
+
"quantization_config": {
|
20 |
+
"autoround_version": "0.6.1.dev",
|
21 |
+
"bits": 4,
|
22 |
+
"block_name_to_quantize": "model.language_model.layers",
|
23 |
+
"data_type": "int",
|
24 |
+
"extra_config": {
|
25 |
+
"model.visual.blocks.0.attn.proj": {
|
26 |
+
"bits": 8,
|
27 |
+
"data_type": "int",
|
28 |
+
"group_size": 128,
|
29 |
+
"sym": true
|
30 |
+
},
|
31 |
+
"model.visual.blocks.0.attn.qkv": {
|
32 |
+
"bits": 8,
|
33 |
+
"data_type": "int",
|
34 |
+
"group_size": 128,
|
35 |
+
"sym": true
|
36 |
+
},
|
37 |
+
"model.visual.blocks.1.attn.proj": {
|
38 |
+
"bits": 8,
|
39 |
+
"data_type": "int",
|
40 |
+
"group_size": 128,
|
41 |
+
"sym": true
|
42 |
+
},
|
43 |
+
"model.visual.blocks.1.attn.qkv": {
|
44 |
+
"bits": 8,
|
45 |
+
"data_type": "int",
|
46 |
+
"group_size": 128,
|
47 |
+
"sym": true
|
48 |
+
},
|
49 |
+
"model.visual.blocks.10.attn.proj": {
|
50 |
+
"bits": 8,
|
51 |
+
"data_type": "int",
|
52 |
+
"group_size": 128,
|
53 |
+
"sym": true
|
54 |
+
},
|
55 |
+
"model.visual.blocks.10.attn.qkv": {
|
56 |
+
"bits": 8,
|
57 |
+
"data_type": "int",
|
58 |
+
"group_size": 128,
|
59 |
+
"sym": true
|
60 |
+
},
|
61 |
+
"model.visual.blocks.11.attn.proj": {
|
62 |
+
"bits": 8,
|
63 |
+
"data_type": "int",
|
64 |
+
"group_size": 128,
|
65 |
+
"sym": true
|
66 |
+
},
|
67 |
+
"model.visual.blocks.11.attn.qkv": {
|
68 |
+
"bits": 8,
|
69 |
+
"data_type": "int",
|
70 |
+
"group_size": 128,
|
71 |
+
"sym": true
|
72 |
+
},
|
73 |
+
"model.visual.blocks.12.attn.proj": {
|
74 |
+
"bits": 8,
|
75 |
+
"data_type": "int",
|
76 |
+
"group_size": 128,
|
77 |
+
"sym": true
|
78 |
+
},
|
79 |
+
"model.visual.blocks.12.attn.qkv": {
|
80 |
+
"bits": 8,
|
81 |
+
"data_type": "int",
|
82 |
+
"group_size": 128,
|
83 |
+
"sym": true
|
84 |
+
},
|
85 |
+
"model.visual.blocks.13.attn.proj": {
|
86 |
+
"bits": 8,
|
87 |
+
"data_type": "int",
|
88 |
+
"group_size": 128,
|
89 |
+
"sym": true
|
90 |
+
},
|
91 |
+
"model.visual.blocks.13.attn.qkv": {
|
92 |
+
"bits": 8,
|
93 |
+
"data_type": "int",
|
94 |
+
"group_size": 128,
|
95 |
+
"sym": true
|
96 |
+
},
|
97 |
+
"model.visual.blocks.14.attn.proj": {
|
98 |
+
"bits": 8,
|
99 |
+
"data_type": "int",
|
100 |
+
"group_size": 128,
|
101 |
+
"sym": true
|
102 |
+
},
|
103 |
+
"model.visual.blocks.14.attn.qkv": {
|
104 |
+
"bits": 8,
|
105 |
+
"data_type": "int",
|
106 |
+
"group_size": 128,
|
107 |
+
"sym": true
|
108 |
+
},
|
109 |
+
"model.visual.blocks.15.attn.proj": {
|
110 |
+
"bits": 8,
|
111 |
+
"data_type": "int",
|
112 |
+
"group_size": 128,
|
113 |
+
"sym": true
|
114 |
+
},
|
115 |
+
"model.visual.blocks.15.attn.qkv": {
|
116 |
+
"bits": 8,
|
117 |
+
"data_type": "int",
|
118 |
+
"group_size": 128,
|
119 |
+
"sym": true
|
120 |
+
},
|
121 |
+
"model.visual.blocks.16.attn.proj": {
|
122 |
+
"bits": 8,
|
123 |
+
"data_type": "int",
|
124 |
+
"group_size": 128,
|
125 |
+
"sym": true
|
126 |
+
},
|
127 |
+
"model.visual.blocks.16.attn.qkv": {
|
128 |
+
"bits": 8,
|
129 |
+
"data_type": "int",
|
130 |
+
"group_size": 128,
|
131 |
+
"sym": true
|
132 |
+
},
|
133 |
+
"model.visual.blocks.17.attn.proj": {
|
134 |
+
"bits": 8,
|
135 |
+
"data_type": "int",
|
136 |
+
"group_size": 128,
|
137 |
+
"sym": true
|
138 |
+
},
|
139 |
+
"model.visual.blocks.17.attn.qkv": {
|
140 |
+
"bits": 8,
|
141 |
+
"data_type": "int",
|
142 |
+
"group_size": 128,
|
143 |
+
"sym": true
|
144 |
+
},
|
145 |
+
"model.visual.blocks.18.attn.proj": {
|
146 |
+
"bits": 8,
|
147 |
+
"data_type": "int",
|
148 |
+
"group_size": 128,
|
149 |
+
"sym": true
|
150 |
+
},
|
151 |
+
"model.visual.blocks.18.attn.qkv": {
|
152 |
+
"bits": 8,
|
153 |
+
"data_type": "int",
|
154 |
+
"group_size": 128,
|
155 |
+
"sym": true
|
156 |
+
},
|
157 |
+
"model.visual.blocks.19.attn.proj": {
|
158 |
+
"bits": 8,
|
159 |
+
"data_type": "int",
|
160 |
+
"group_size": 128,
|
161 |
+
"sym": true
|
162 |
+
},
|
163 |
+
"model.visual.blocks.19.attn.qkv": {
|
164 |
+
"bits": 8,
|
165 |
+
"data_type": "int",
|
166 |
+
"group_size": 128,
|
167 |
+
"sym": true
|
168 |
+
},
|
169 |
+
"model.visual.blocks.2.attn.proj": {
|
170 |
+
"bits": 8,
|
171 |
+
"data_type": "int",
|
172 |
+
"group_size": 128,
|
173 |
+
"sym": true
|
174 |
+
},
|
175 |
+
"model.visual.blocks.2.attn.qkv": {
|
176 |
+
"bits": 8,
|
177 |
+
"data_type": "int",
|
178 |
+
"group_size": 128,
|
179 |
+
"sym": true
|
180 |
+
},
|
181 |
+
"model.visual.blocks.20.attn.proj": {
|
182 |
+
"bits": 8,
|
183 |
+
"data_type": "int",
|
184 |
+
"group_size": 128,
|
185 |
+
"sym": true
|
186 |
+
},
|
187 |
+
"model.visual.blocks.20.attn.qkv": {
|
188 |
+
"bits": 8,
|
189 |
+
"data_type": "int",
|
190 |
+
"group_size": 128,
|
191 |
+
"sym": true
|
192 |
+
},
|
193 |
+
"model.visual.blocks.21.attn.proj": {
|
194 |
+
"bits": 8,
|
195 |
+
"data_type": "int",
|
196 |
+
"group_size": 128,
|
197 |
+
"sym": true
|
198 |
+
},
|
199 |
+
"model.visual.blocks.21.attn.qkv": {
|
200 |
+
"bits": 8,
|
201 |
+
"data_type": "int",
|
202 |
+
"group_size": 128,
|
203 |
+
"sym": true
|
204 |
+
},
|
205 |
+
"model.visual.blocks.22.attn.proj": {
|
206 |
+
"bits": 8,
|
207 |
+
"data_type": "int",
|
208 |
+
"group_size": 128,
|
209 |
+
"sym": true
|
210 |
+
},
|
211 |
+
"model.visual.blocks.22.attn.qkv": {
|
212 |
+
"bits": 8,
|
213 |
+
"data_type": "int",
|
214 |
+
"group_size": 128,
|
215 |
+
"sym": true
|
216 |
+
},
|
217 |
+
"model.visual.blocks.23.attn.proj": {
|
218 |
+
"bits": 8,
|
219 |
+
"data_type": "int",
|
220 |
+
"group_size": 128,
|
221 |
+
"sym": true
|
222 |
+
},
|
223 |
+
"model.visual.blocks.23.attn.qkv": {
|
224 |
+
"bits": 8,
|
225 |
+
"data_type": "int",
|
226 |
+
"group_size": 128,
|
227 |
+
"sym": true
|
228 |
+
},
|
229 |
+
"model.visual.blocks.24.attn.proj": {
|
230 |
+
"bits": 8,
|
231 |
+
"data_type": "int",
|
232 |
+
"group_size": 128,
|
233 |
+
"sym": true
|
234 |
+
},
|
235 |
+
"model.visual.blocks.24.attn.qkv": {
|
236 |
+
"bits": 8,
|
237 |
+
"data_type": "int",
|
238 |
+
"group_size": 128,
|
239 |
+
"sym": true
|
240 |
+
},
|
241 |
+
"model.visual.blocks.25.attn.proj": {
|
242 |
+
"bits": 8,
|
243 |
+
"data_type": "int",
|
244 |
+
"group_size": 128,
|
245 |
+
"sym": true
|
246 |
+
},
|
247 |
+
"model.visual.blocks.25.attn.qkv": {
|
248 |
+
"bits": 8,
|
249 |
+
"data_type": "int",
|
250 |
+
"group_size": 128,
|
251 |
+
"sym": true
|
252 |
+
},
|
253 |
+
"model.visual.blocks.26.attn.proj": {
|
254 |
+
"bits": 8,
|
255 |
+
"data_type": "int",
|
256 |
+
"group_size": 128,
|
257 |
+
"sym": true
|
258 |
+
},
|
259 |
+
"model.visual.blocks.26.attn.qkv": {
|
260 |
+
"bits": 8,
|
261 |
+
"data_type": "int",
|
262 |
+
"group_size": 128,
|
263 |
+
"sym": true
|
264 |
+
},
|
265 |
+
"model.visual.blocks.27.attn.proj": {
|
266 |
+
"bits": 8,
|
267 |
+
"data_type": "int",
|
268 |
+
"group_size": 128,
|
269 |
+
"sym": true
|
270 |
+
},
|
271 |
+
"model.visual.blocks.27.attn.qkv": {
|
272 |
+
"bits": 8,
|
273 |
+
"data_type": "int",
|
274 |
+
"group_size": 128,
|
275 |
+
"sym": true
|
276 |
+
},
|
277 |
+
"model.visual.blocks.28.attn.proj": {
|
278 |
+
"bits": 8,
|
279 |
+
"data_type": "int",
|
280 |
+
"group_size": 128,
|
281 |
+
"sym": true
|
282 |
+
},
|
283 |
+
"model.visual.blocks.28.attn.qkv": {
|
284 |
+
"bits": 8,
|
285 |
+
"data_type": "int",
|
286 |
+
"group_size": 128,
|
287 |
+
"sym": true
|
288 |
+
},
|
289 |
+
"model.visual.blocks.29.attn.proj": {
|
290 |
+
"bits": 8,
|
291 |
+
"data_type": "int",
|
292 |
+
"group_size": 128,
|
293 |
+
"sym": true
|
294 |
+
},
|
295 |
+
"model.visual.blocks.29.attn.qkv": {
|
296 |
+
"bits": 8,
|
297 |
+
"data_type": "int",
|
298 |
+
"group_size": 128,
|
299 |
+
"sym": true
|
300 |
+
},
|
301 |
+
"model.visual.blocks.3.attn.proj": {
|
302 |
+
"bits": 8,
|
303 |
+
"data_type": "int",
|
304 |
+
"group_size": 128,
|
305 |
+
"sym": true
|
306 |
+
},
|
307 |
+
"model.visual.blocks.3.attn.qkv": {
|
308 |
+
"bits": 8,
|
309 |
+
"data_type": "int",
|
310 |
+
"group_size": 128,
|
311 |
+
"sym": true
|
312 |
+
},
|
313 |
+
"model.visual.blocks.30.attn.proj": {
|
314 |
+
"bits": 8,
|
315 |
+
"data_type": "int",
|
316 |
+
"group_size": 128,
|
317 |
+
"sym": true
|
318 |
+
},
|
319 |
+
"model.visual.blocks.30.attn.qkv": {
|
320 |
+
"bits": 8,
|
321 |
+
"data_type": "int",
|
322 |
+
"group_size": 128,
|
323 |
+
"sym": true
|
324 |
+
},
|
325 |
+
"model.visual.blocks.31.attn.proj": {
|
326 |
+
"bits": 8,
|
327 |
+
"data_type": "int",
|
328 |
+
"group_size": 128,
|
329 |
+
"sym": true
|
330 |
+
},
|
331 |
+
"model.visual.blocks.31.attn.qkv": {
|
332 |
+
"bits": 8,
|
333 |
+
"data_type": "int",
|
334 |
+
"group_size": 128,
|
335 |
+
"sym": true
|
336 |
+
},
|
337 |
+
"model.visual.blocks.4.attn.proj": {
|
338 |
+
"bits": 8,
|
339 |
+
"data_type": "int",
|
340 |
+
"group_size": 128,
|
341 |
+
"sym": true
|
342 |
+
},
|
343 |
+
"model.visual.blocks.4.attn.qkv": {
|
344 |
+
"bits": 8,
|
345 |
+
"data_type": "int",
|
346 |
+
"group_size": 128,
|
347 |
+
"sym": true
|
348 |
+
},
|
349 |
+
"model.visual.blocks.5.attn.proj": {
|
350 |
+
"bits": 8,
|
351 |
+
"data_type": "int",
|
352 |
+
"group_size": 128,
|
353 |
+
"sym": true
|
354 |
+
},
|
355 |
+
"model.visual.blocks.5.attn.qkv": {
|
356 |
+
"bits": 8,
|
357 |
+
"data_type": "int",
|
358 |
+
"group_size": 128,
|
359 |
+
"sym": true
|
360 |
+
},
|
361 |
+
"model.visual.blocks.6.attn.proj": {
|
362 |
+
"bits": 8,
|
363 |
+
"data_type": "int",
|
364 |
+
"group_size": 128,
|
365 |
+
"sym": true
|
366 |
+
},
|
367 |
+
"model.visual.blocks.6.attn.qkv": {
|
368 |
+
"bits": 8,
|
369 |
+
"data_type": "int",
|
370 |
+
"group_size": 128,
|
371 |
+
"sym": true
|
372 |
+
},
|
373 |
+
"model.visual.blocks.7.attn.proj": {
|
374 |
+
"bits": 8,
|
375 |
+
"data_type": "int",
|
376 |
+
"group_size": 128,
|
377 |
+
"sym": true
|
378 |
+
},
|
379 |
+
"model.visual.blocks.7.attn.qkv": {
|
380 |
+
"bits": 8,
|
381 |
+
"data_type": "int",
|
382 |
+
"group_size": 128,
|
383 |
+
"sym": true
|
384 |
+
},
|
385 |
+
"model.visual.blocks.8.attn.proj": {
|
386 |
+
"bits": 8,
|
387 |
+
"data_type": "int",
|
388 |
+
"group_size": 128,
|
389 |
+
"sym": true
|
390 |
+
},
|
391 |
+
"model.visual.blocks.8.attn.qkv": {
|
392 |
+
"bits": 8,
|
393 |
+
"data_type": "int",
|
394 |
+
"group_size": 128,
|
395 |
+
"sym": true
|
396 |
+
},
|
397 |
+
"model.visual.blocks.9.attn.proj": {
|
398 |
+
"bits": 8,
|
399 |
+
"data_type": "int",
|
400 |
+
"group_size": 128,
|
401 |
+
"sym": true
|
402 |
+
},
|
403 |
+
"model.visual.blocks.9.attn.qkv": {
|
404 |
+
"bits": 8,
|
405 |
+
"data_type": "int",
|
406 |
+
"group_size": 128,
|
407 |
+
"sym": true
|
408 |
+
},
|
409 |
+
"model.visual.merger.mlp.0": {
|
410 |
+
"bits": 8,
|
411 |
+
"data_type": "int",
|
412 |
+
"group_size": 128,
|
413 |
+
"sym": true
|
414 |
+
},
|
415 |
+
"model.visual.merger.mlp.2": {
|
416 |
+
"bits": 8,
|
417 |
+
"data_type": "int",
|
418 |
+
"group_size": 128,
|
419 |
+
"sym": true
|
420 |
+
}
|
421 |
+
},
|
422 |
+
"group_size": 128,
|
423 |
+
"packing_format": "auto_round:auto_gptq",
|
424 |
+
"quant_method": "auto-round",
|
425 |
+
"sym": true
|
426 |
+
},
|
427 |
+
"rms_norm_eps": 1e-06,
|
428 |
+
"rope_scaling": {
|
429 |
+
"mrope_section": [
|
430 |
+
16,
|
431 |
+
24,
|
432 |
+
24
|
433 |
+
],
|
434 |
+
"rope_type": "default",
|
435 |
+
"type": "default"
|
436 |
+
},
|
437 |
+
"rope_theta": 1000000.0,
|
438 |
+
"sliding_window": 32768,
|
439 |
+
"text_config": {
|
440 |
+
"architectures": [
|
441 |
+
"Qwen2_5_VLForConditionalGeneration"
|
442 |
+
],
|
443 |
+
"attention_dropout": 0.0,
|
444 |
+
"bos_token_id": 151643,
|
445 |
+
"eos_token_id": 151645,
|
446 |
+
"hidden_act": "silu",
|
447 |
+
"hidden_size": 3584,
|
448 |
+
"image_token_id": null,
|
449 |
+
"initializer_range": 0.02,
|
450 |
+
"intermediate_size": 18944,
|
451 |
+
"layer_types": [
|
452 |
+
"full_attention",
|
453 |
+
"full_attention",
|
454 |
+
"full_attention",
|
455 |
+
"full_attention",
|
456 |
+
"full_attention",
|
457 |
+
"full_attention",
|
458 |
+
"full_attention",
|
459 |
+
"full_attention",
|
460 |
+
"full_attention",
|
461 |
+
"full_attention",
|
462 |
+
"full_attention",
|
463 |
+
"full_attention",
|
464 |
+
"full_attention",
|
465 |
+
"full_attention",
|
466 |
+
"full_attention",
|
467 |
+
"full_attention",
|
468 |
+
"full_attention",
|
469 |
+
"full_attention",
|
470 |
+
"full_attention",
|
471 |
+
"full_attention",
|
472 |
+
"full_attention",
|
473 |
+
"full_attention",
|
474 |
+
"full_attention",
|
475 |
+
"full_attention",
|
476 |
+
"full_attention",
|
477 |
+
"full_attention",
|
478 |
+
"full_attention",
|
479 |
+
"full_attention"
|
480 |
+
],
|
481 |
+
"max_position_embeddings": 128000,
|
482 |
+
"max_window_layers": 28,
|
483 |
+
"model_type": "qwen2_5_vl_text",
|
484 |
+
"num_attention_heads": 28,
|
485 |
+
"num_hidden_layers": 28,
|
486 |
+
"num_key_value_heads": 4,
|
487 |
+
"rms_norm_eps": 1e-06,
|
488 |
+
"rope_scaling": {
|
489 |
+
"mrope_section": [
|
490 |
+
16,
|
491 |
+
24,
|
492 |
+
24
|
493 |
+
],
|
494 |
+
"rope_type": "default",
|
495 |
+
"type": "default"
|
496 |
+
},
|
497 |
+
"rope_theta": 1000000.0,
|
498 |
+
"sliding_window": null,
|
499 |
+
"torch_dtype": "bfloat16",
|
500 |
+
"use_cache": true,
|
501 |
+
"use_sliding_window": false,
|
502 |
+
"video_token_id": null,
|
503 |
+
"vision_end_token_id": 151653,
|
504 |
+
"vision_start_token_id": 151652,
|
505 |
+
"vision_token_id": 151654,
|
506 |
+
"vocab_size": 152064
|
507 |
+
},
|
508 |
+
"tie_word_embeddings": false,
|
509 |
+
"torch_dtype": "bfloat16",
|
510 |
+
"transformers_version": "4.53.2",
|
511 |
+
"use_cache": true,
|
512 |
+
"use_sliding_window": false,
|
513 |
+
"video_token_id": 151656,
|
514 |
+
"vision_config": {
|
515 |
+
"depth": 32,
|
516 |
+
"fullatt_block_indexes": [
|
517 |
+
7,
|
518 |
+
15,
|
519 |
+
23,
|
520 |
+
31
|
521 |
+
],
|
522 |
+
"hidden_act": "silu",
|
523 |
+
"hidden_size": 1280,
|
524 |
+
"in_channels": 3,
|
525 |
+
"in_chans": 3,
|
526 |
+
"initializer_range": 0.02,
|
527 |
+
"intermediate_size": 3420,
|
528 |
+
"model_type": "qwen2_5_vl",
|
529 |
+
"num_heads": 16,
|
530 |
+
"out_hidden_size": 3584,
|
531 |
+
"patch_size": 14,
|
532 |
+
"spatial_merge_size": 2,
|
533 |
+
"spatial_patch_size": 14,
|
534 |
+
"temporal_patch_size": 2,
|
535 |
+
"tokens_per_second": 2,
|
536 |
+
"window_size": 112
|
537 |
+
},
|
538 |
+
"vision_end_token_id": 151653,
|
539 |
+
"vision_start_token_id": 151652,
|
540 |
+
"vision_token_id": 151654,
|
541 |
+
"vocab_size": 152064
|
542 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"repetition_penalty": 1.05,
|
10 |
+
"temperature": 1e-06,
|
11 |
+
"transformers_version": "4.53.2"
|
12 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd2ab079f05cec6c675f6179463b1fa78e97513a1f744fa959407eae7e7e0cab
|
3 |
+
size 4995423000
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86048bfc886649f5e49b4cd4ccb47ca0772b30cbc0448b4c0e572f9e511d825d
|
3 |
+
size 1680243544
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_rgb": true,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.48145466,
|
8 |
+
0.4578275,
|
9 |
+
0.40821073
|
10 |
+
],
|
11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.26862954,
|
14 |
+
0.26130258,
|
15 |
+
0.27577711
|
16 |
+
],
|
17 |
+
"max_pixels": 12845056,
|
18 |
+
"merge_size": 2,
|
19 |
+
"min_pixels": 3136,
|
20 |
+
"patch_size": 14,
|
21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
22 |
+
"resample": 3,
|
23 |
+
"rescale_factor": 0.00392156862745098,
|
24 |
+
"size": {
|
25 |
+
"longest_edge": 12845056,
|
26 |
+
"shortest_edge": 3136
|
27 |
+
},
|
28 |
+
"temporal_patch_size": 2
|
29 |
+
}
|
quantization_config.json
ADDED
@@ -0,0 +1,408 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 4,
|
3 |
+
"group_size": 128,
|
4 |
+
"sym": true,
|
5 |
+
"data_type": "int",
|
6 |
+
"autoround_version": "0.6.1.dev",
|
7 |
+
"block_name_to_quantize": "model.language_model.layers",
|
8 |
+
"quant_method": "auto-round",
|
9 |
+
"packing_format": "auto_round:auto_gptq",
|
10 |
+
"extra_config": {
|
11 |
+
"model.visual.blocks.0.attn.qkv": {
|
12 |
+
"bits": 8,
|
13 |
+
"data_type": "int",
|
14 |
+
"group_size": 128,
|
15 |
+
"sym": true
|
16 |
+
},
|
17 |
+
"model.visual.blocks.0.attn.proj": {
|
18 |
+
"bits": 8,
|
19 |
+
"data_type": "int",
|
20 |
+
"group_size": 128,
|
21 |
+
"sym": true
|
22 |
+
},
|
23 |
+
"model.visual.blocks.1.attn.qkv": {
|
24 |
+
"bits": 8,
|
25 |
+
"data_type": "int",
|
26 |
+
"group_size": 128,
|
27 |
+
"sym": true
|
28 |
+
},
|
29 |
+
"model.visual.blocks.1.attn.proj": {
|
30 |
+
"bits": 8,
|
31 |
+
"data_type": "int",
|
32 |
+
"group_size": 128,
|
33 |
+
"sym": true
|
34 |
+
},
|
35 |
+
"model.visual.blocks.2.attn.qkv": {
|
36 |
+
"bits": 8,
|
37 |
+
"data_type": "int",
|
38 |
+
"group_size": 128,
|
39 |
+
"sym": true
|
40 |
+
},
|
41 |
+
"model.visual.blocks.2.attn.proj": {
|
42 |
+
"bits": 8,
|
43 |
+
"data_type": "int",
|
44 |
+
"group_size": 128,
|
45 |
+
"sym": true
|
46 |
+
},
|
47 |
+
"model.visual.blocks.3.attn.qkv": {
|
48 |
+
"bits": 8,
|
49 |
+
"data_type": "int",
|
50 |
+
"group_size": 128,
|
51 |
+
"sym": true
|
52 |
+
},
|
53 |
+
"model.visual.blocks.3.attn.proj": {
|
54 |
+
"bits": 8,
|
55 |
+
"data_type": "int",
|
56 |
+
"group_size": 128,
|
57 |
+
"sym": true
|
58 |
+
},
|
59 |
+
"model.visual.blocks.4.attn.qkv": {
|
60 |
+
"bits": 8,
|
61 |
+
"data_type": "int",
|
62 |
+
"group_size": 128,
|
63 |
+
"sym": true
|
64 |
+
},
|
65 |
+
"model.visual.blocks.4.attn.proj": {
|
66 |
+
"bits": 8,
|
67 |
+
"data_type": "int",
|
68 |
+
"group_size": 128,
|
69 |
+
"sym": true
|
70 |
+
},
|
71 |
+
"model.visual.blocks.5.attn.qkv": {
|
72 |
+
"bits": 8,
|
73 |
+
"data_type": "int",
|
74 |
+
"group_size": 128,
|
75 |
+
"sym": true
|
76 |
+
},
|
77 |
+
"model.visual.blocks.5.attn.proj": {
|
78 |
+
"bits": 8,
|
79 |
+
"data_type": "int",
|
80 |
+
"group_size": 128,
|
81 |
+
"sym": true
|
82 |
+
},
|
83 |
+
"model.visual.blocks.6.attn.qkv": {
|
84 |
+
"bits": 8,
|
85 |
+
"data_type": "int",
|
86 |
+
"group_size": 128,
|
87 |
+
"sym": true
|
88 |
+
},
|
89 |
+
"model.visual.blocks.6.attn.proj": {
|
90 |
+
"bits": 8,
|
91 |
+
"data_type": "int",
|
92 |
+
"group_size": 128,
|
93 |
+
"sym": true
|
94 |
+
},
|
95 |
+
"model.visual.blocks.7.attn.qkv": {
|
96 |
+
"bits": 8,
|
97 |
+
"data_type": "int",
|
98 |
+
"group_size": 128,
|
99 |
+
"sym": true
|
100 |
+
},
|
101 |
+
"model.visual.blocks.7.attn.proj": {
|
102 |
+
"bits": 8,
|
103 |
+
"data_type": "int",
|
104 |
+
"group_size": 128,
|
105 |
+
"sym": true
|
106 |
+
},
|
107 |
+
"model.visual.blocks.8.attn.qkv": {
|
108 |
+
"bits": 8,
|
109 |
+
"data_type": "int",
|
110 |
+
"group_size": 128,
|
111 |
+
"sym": true
|
112 |
+
},
|
113 |
+
"model.visual.blocks.8.attn.proj": {
|
114 |
+
"bits": 8,
|
115 |
+
"data_type": "int",
|
116 |
+
"group_size": 128,
|
117 |
+
"sym": true
|
118 |
+
},
|
119 |
+
"model.visual.blocks.9.attn.qkv": {
|
120 |
+
"bits": 8,
|
121 |
+
"data_type": "int",
|
122 |
+
"group_size": 128,
|
123 |
+
"sym": true
|
124 |
+
},
|
125 |
+
"model.visual.blocks.9.attn.proj": {
|
126 |
+
"bits": 8,
|
127 |
+
"data_type": "int",
|
128 |
+
"group_size": 128,
|
129 |
+
"sym": true
|
130 |
+
},
|
131 |
+
"model.visual.blocks.10.attn.qkv": {
|
132 |
+
"bits": 8,
|
133 |
+
"data_type": "int",
|
134 |
+
"group_size": 128,
|
135 |
+
"sym": true
|
136 |
+
},
|
137 |
+
"model.visual.blocks.10.attn.proj": {
|
138 |
+
"bits": 8,
|
139 |
+
"data_type": "int",
|
140 |
+
"group_size": 128,
|
141 |
+
"sym": true
|
142 |
+
},
|
143 |
+
"model.visual.blocks.11.attn.qkv": {
|
144 |
+
"bits": 8,
|
145 |
+
"data_type": "int",
|
146 |
+
"group_size": 128,
|
147 |
+
"sym": true
|
148 |
+
},
|
149 |
+
"model.visual.blocks.11.attn.proj": {
|
150 |
+
"bits": 8,
|
151 |
+
"data_type": "int",
|
152 |
+
"group_size": 128,
|
153 |
+
"sym": true
|
154 |
+
},
|
155 |
+
"model.visual.blocks.12.attn.qkv": {
|
156 |
+
"bits": 8,
|
157 |
+
"data_type": "int",
|
158 |
+
"group_size": 128,
|
159 |
+
"sym": true
|
160 |
+
},
|
161 |
+
"model.visual.blocks.12.attn.proj": {
|
162 |
+
"bits": 8,
|
163 |
+
"data_type": "int",
|
164 |
+
"group_size": 128,
|
165 |
+
"sym": true
|
166 |
+
},
|
167 |
+
"model.visual.blocks.13.attn.qkv": {
|
168 |
+
"bits": 8,
|
169 |
+
"data_type": "int",
|
170 |
+
"group_size": 128,
|
171 |
+
"sym": true
|
172 |
+
},
|
173 |
+
"model.visual.blocks.13.attn.proj": {
|
174 |
+
"bits": 8,
|
175 |
+
"data_type": "int",
|
176 |
+
"group_size": 128,
|
177 |
+
"sym": true
|
178 |
+
},
|
179 |
+
"model.visual.blocks.14.attn.qkv": {
|
180 |
+
"bits": 8,
|
181 |
+
"data_type": "int",
|
182 |
+
"group_size": 128,
|
183 |
+
"sym": true
|
184 |
+
},
|
185 |
+
"model.visual.blocks.14.attn.proj": {
|
186 |
+
"bits": 8,
|
187 |
+
"data_type": "int",
|
188 |
+
"group_size": 128,
|
189 |
+
"sym": true
|
190 |
+
},
|
191 |
+
"model.visual.blocks.15.attn.qkv": {
|
192 |
+
"bits": 8,
|
193 |
+
"data_type": "int",
|
194 |
+
"group_size": 128,
|
195 |
+
"sym": true
|
196 |
+
},
|
197 |
+
"model.visual.blocks.15.attn.proj": {
|
198 |
+
"bits": 8,
|
199 |
+
"data_type": "int",
|
200 |
+
"group_size": 128,
|
201 |
+
"sym": true
|
202 |
+
},
|
203 |
+
"model.visual.blocks.16.attn.qkv": {
|
204 |
+
"bits": 8,
|
205 |
+
"data_type": "int",
|
206 |
+
"group_size": 128,
|
207 |
+
"sym": true
|
208 |
+
},
|
209 |
+
"model.visual.blocks.16.attn.proj": {
|
210 |
+
"bits": 8,
|
211 |
+
"data_type": "int",
|
212 |
+
"group_size": 128,
|
213 |
+
"sym": true
|
214 |
+
},
|
215 |
+
"model.visual.blocks.17.attn.qkv": {
|
216 |
+
"bits": 8,
|
217 |
+
"data_type": "int",
|
218 |
+
"group_size": 128,
|
219 |
+
"sym": true
|
220 |
+
},
|
221 |
+
"model.visual.blocks.17.attn.proj": {
|
222 |
+
"bits": 8,
|
223 |
+
"data_type": "int",
|
224 |
+
"group_size": 128,
|
225 |
+
"sym": true
|
226 |
+
},
|
227 |
+
"model.visual.blocks.18.attn.qkv": {
|
228 |
+
"bits": 8,
|
229 |
+
"data_type": "int",
|
230 |
+
"group_size": 128,
|
231 |
+
"sym": true
|
232 |
+
},
|
233 |
+
"model.visual.blocks.18.attn.proj": {
|
234 |
+
"bits": 8,
|
235 |
+
"data_type": "int",
|
236 |
+
"group_size": 128,
|
237 |
+
"sym": true
|
238 |
+
},
|
239 |
+
"model.visual.blocks.19.attn.qkv": {
|
240 |
+
"bits": 8,
|
241 |
+
"data_type": "int",
|
242 |
+
"group_size": 128,
|
243 |
+
"sym": true
|
244 |
+
},
|
245 |
+
"model.visual.blocks.19.attn.proj": {
|
246 |
+
"bits": 8,
|
247 |
+
"data_type": "int",
|
248 |
+
"group_size": 128,
|
249 |
+
"sym": true
|
250 |
+
},
|
251 |
+
"model.visual.blocks.20.attn.qkv": {
|
252 |
+
"bits": 8,
|
253 |
+
"data_type": "int",
|
254 |
+
"group_size": 128,
|
255 |
+
"sym": true
|
256 |
+
},
|
257 |
+
"model.visual.blocks.20.attn.proj": {
|
258 |
+
"bits": 8,
|
259 |
+
"data_type": "int",
|
260 |
+
"group_size": 128,
|
261 |
+
"sym": true
|
262 |
+
},
|
263 |
+
"model.visual.blocks.21.attn.qkv": {
|
264 |
+
"bits": 8,
|
265 |
+
"data_type": "int",
|
266 |
+
"group_size": 128,
|
267 |
+
"sym": true
|
268 |
+
},
|
269 |
+
"model.visual.blocks.21.attn.proj": {
|
270 |
+
"bits": 8,
|
271 |
+
"data_type": "int",
|
272 |
+
"group_size": 128,
|
273 |
+
"sym": true
|
274 |
+
},
|
275 |
+
"model.visual.blocks.22.attn.qkv": {
|
276 |
+
"bits": 8,
|
277 |
+
"data_type": "int",
|
278 |
+
"group_size": 128,
|
279 |
+
"sym": true
|
280 |
+
},
|
281 |
+
"model.visual.blocks.22.attn.proj": {
|
282 |
+
"bits": 8,
|
283 |
+
"data_type": "int",
|
284 |
+
"group_size": 128,
|
285 |
+
"sym": true
|
286 |
+
},
|
287 |
+
"model.visual.blocks.23.attn.qkv": {
|
288 |
+
"bits": 8,
|
289 |
+
"data_type": "int",
|
290 |
+
"group_size": 128,
|
291 |
+
"sym": true
|
292 |
+
},
|
293 |
+
"model.visual.blocks.23.attn.proj": {
|
294 |
+
"bits": 8,
|
295 |
+
"data_type": "int",
|
296 |
+
"group_size": 128,
|
297 |
+
"sym": true
|
298 |
+
},
|
299 |
+
"model.visual.blocks.24.attn.qkv": {
|
300 |
+
"bits": 8,
|
301 |
+
"data_type": "int",
|
302 |
+
"group_size": 128,
|
303 |
+
"sym": true
|
304 |
+
},
|
305 |
+
"model.visual.blocks.24.attn.proj": {
|
306 |
+
"bits": 8,
|
307 |
+
"data_type": "int",
|
308 |
+
"group_size": 128,
|
309 |
+
"sym": true
|
310 |
+
},
|
311 |
+
"model.visual.blocks.25.attn.qkv": {
|
312 |
+
"bits": 8,
|
313 |
+
"data_type": "int",
|
314 |
+
"group_size": 128,
|
315 |
+
"sym": true
|
316 |
+
},
|
317 |
+
"model.visual.blocks.25.attn.proj": {
|
318 |
+
"bits": 8,
|
319 |
+
"data_type": "int",
|
320 |
+
"group_size": 128,
|
321 |
+
"sym": true
|
322 |
+
},
|
323 |
+
"model.visual.blocks.26.attn.qkv": {
|
324 |
+
"bits": 8,
|
325 |
+
"data_type": "int",
|
326 |
+
"group_size": 128,
|
327 |
+
"sym": true
|
328 |
+
},
|
329 |
+
"model.visual.blocks.26.attn.proj": {
|
330 |
+
"bits": 8,
|
331 |
+
"data_type": "int",
|
332 |
+
"group_size": 128,
|
333 |
+
"sym": true
|
334 |
+
},
|
335 |
+
"model.visual.blocks.27.attn.qkv": {
|
336 |
+
"bits": 8,
|
337 |
+
"data_type": "int",
|
338 |
+
"group_size": 128,
|
339 |
+
"sym": true
|
340 |
+
},
|
341 |
+
"model.visual.blocks.27.attn.proj": {
|
342 |
+
"bits": 8,
|
343 |
+
"data_type": "int",
|
344 |
+
"group_size": 128,
|
345 |
+
"sym": true
|
346 |
+
},
|
347 |
+
"model.visual.blocks.28.attn.qkv": {
|
348 |
+
"bits": 8,
|
349 |
+
"data_type": "int",
|
350 |
+
"group_size": 128,
|
351 |
+
"sym": true
|
352 |
+
},
|
353 |
+
"model.visual.blocks.28.attn.proj": {
|
354 |
+
"bits": 8,
|
355 |
+
"data_type": "int",
|
356 |
+
"group_size": 128,
|
357 |
+
"sym": true
|
358 |
+
},
|
359 |
+
"model.visual.blocks.29.attn.qkv": {
|
360 |
+
"bits": 8,
|
361 |
+
"data_type": "int",
|
362 |
+
"group_size": 128,
|
363 |
+
"sym": true
|
364 |
+
},
|
365 |
+
"model.visual.blocks.29.attn.proj": {
|
366 |
+
"bits": 8,
|
367 |
+
"data_type": "int",
|
368 |
+
"group_size": 128,
|
369 |
+
"sym": true
|
370 |
+
},
|
371 |
+
"model.visual.blocks.30.attn.qkv": {
|
372 |
+
"bits": 8,
|
373 |
+
"data_type": "int",
|
374 |
+
"group_size": 128,
|
375 |
+
"sym": true
|
376 |
+
},
|
377 |
+
"model.visual.blocks.30.attn.proj": {
|
378 |
+
"bits": 8,
|
379 |
+
"data_type": "int",
|
380 |
+
"group_size": 128,
|
381 |
+
"sym": true
|
382 |
+
},
|
383 |
+
"model.visual.blocks.31.attn.qkv": {
|
384 |
+
"bits": 8,
|
385 |
+
"data_type": "int",
|
386 |
+
"group_size": 128,
|
387 |
+
"sym": true
|
388 |
+
},
|
389 |
+
"model.visual.blocks.31.attn.proj": {
|
390 |
+
"bits": 8,
|
391 |
+
"data_type": "int",
|
392 |
+
"group_size": 128,
|
393 |
+
"sym": true
|
394 |
+
},
|
395 |
+
"model.visual.merger.mlp.0": {
|
396 |
+
"bits": 8,
|
397 |
+
"data_type": "int",
|
398 |
+
"group_size": 128,
|
399 |
+
"sym": true
|
400 |
+
},
|
401 |
+
"model.visual.merger.mlp.2": {
|
402 |
+
"bits": 8,
|
403 |
+
"data_type": "int",
|
404 |
+
"group_size": 128,
|
405 |
+
"sym": true
|
406 |
+
}
|
407 |
+
}
|
408 |
+
}
|
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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
3 |
+
size 11421896
|
tokenizer_config.json
ADDED
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"clean_up_tokenization_spaces": false,
|
199 |
+
"eos_token": "<|im_end|>",
|
200 |
+
"errors": "replace",
|
201 |
+
"extra_special_tokens": {},
|
202 |
+
"model_max_length": 131072,
|
203 |
+
"pad_token": "<|endoftext|>",
|
204 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
205 |
+
"split_special_tokens": false,
|
206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
207 |
+
"unk_token": null
|
208 |
+
}
|
video_preprocessor_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_pad": null,
|
10 |
+
"do_rescale": true,
|
11 |
+
"do_resize": true,
|
12 |
+
"do_sample_frames": false,
|
13 |
+
"fps": null,
|
14 |
+
"image_mean": [
|
15 |
+
0.48145466,
|
16 |
+
0.4578275,
|
17 |
+
0.40821073
|
18 |
+
],
|
19 |
+
"image_std": [
|
20 |
+
0.26862954,
|
21 |
+
0.26130258,
|
22 |
+
0.27577711
|
23 |
+
],
|
24 |
+
"input_data_format": null,
|
25 |
+
"max_frames": 768,
|
26 |
+
"max_pixels": 12845056,
|
27 |
+
"merge_size": 2,
|
28 |
+
"min_frames": 4,
|
29 |
+
"min_pixels": 3136,
|
30 |
+
"num_frames": null,
|
31 |
+
"patch_size": 14,
|
32 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
33 |
+
"resample": 3,
|
34 |
+
"rescale_factor": 0.00392156862745098,
|
35 |
+
"size": {
|
36 |
+
"longest_edge": 12845056,
|
37 |
+
"shortest_edge": 3136
|
38 |
+
},
|
39 |
+
"size_divisor": null,
|
40 |
+
"temporal_patch_size": 2,
|
41 |
+
"video_metadata": null,
|
42 |
+
"video_processor_type": "Qwen2VLVideoProcessor"
|
43 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|