Commit
·
0d21073
1
Parent(s):
152b8d1
Update files to match base model keeping quant_config intact
Browse files- added_tokens.json +0 -24
- chat_template.json +2 -2
- config.json +29 -223
- generation_config.json +4 -5
- merges.txt +0 -1
- preprocessor_config.json +7 -17
- special_tokens_map.json +0 -31
- tokenizer.json +2 -2
- tokenizer_config.json +3 -5
added_tokens.json
DELETED
@@ -1,24 +0,0 @@
|
|
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.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
}
|
|
|
1 |
{
|
2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
3 |
+
}
|
config.json
CHANGED
@@ -1,14 +1,17 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "Qwen/Qwen2.5-VL-72B-Instruct",
|
3 |
"architectures": [
|
4 |
"Qwen2_5_VLForConditionalGeneration"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 151643,
|
8 |
"eos_token_id": 151645,
|
|
|
|
|
|
|
|
|
|
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 8192,
|
11 |
-
"image_token_id": 151655,
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 29568,
|
14 |
"max_position_embeddings": 128000,
|
@@ -17,239 +20,42 @@
|
|
17 |
"num_attention_heads": 64,
|
18 |
"num_hidden_layers": 80,
|
19 |
"num_key_value_heads": 8,
|
20 |
-
"quantization_config": {
|
21 |
-
"config_groups": {
|
22 |
-
"group_0": {
|
23 |
-
"input_activations": {
|
24 |
-
"actorder": null,
|
25 |
-
"block_structure": null,
|
26 |
-
"dynamic": true,
|
27 |
-
"group_size": null,
|
28 |
-
"num_bits": 8,
|
29 |
-
"observer": null,
|
30 |
-
"observer_kwargs": {},
|
31 |
-
"strategy": "token",
|
32 |
-
"symmetric": true,
|
33 |
-
"type": "int"
|
34 |
-
},
|
35 |
-
"output_activations": null,
|
36 |
-
"targets": [
|
37 |
-
"Linear"
|
38 |
-
],
|
39 |
-
"weights": {
|
40 |
-
"actorder": null,
|
41 |
-
"block_structure": null,
|
42 |
-
"dynamic": false,
|
43 |
-
"group_size": null,
|
44 |
-
"num_bits": 8,
|
45 |
-
"observer": "minmax",
|
46 |
-
"observer_kwargs": {},
|
47 |
-
"strategy": "channel",
|
48 |
-
"symmetric": true,
|
49 |
-
"type": "int"
|
50 |
-
}
|
51 |
-
}
|
52 |
-
},
|
53 |
-
"format": "int-quantized",
|
54 |
-
"global_compression_ratio": 1.323305644571225,
|
55 |
-
"ignore": [
|
56 |
-
"visual.blocks.0.attn.qkv",
|
57 |
-
"visual.blocks.0.attn.proj",
|
58 |
-
"visual.blocks.0.mlp.gate_proj",
|
59 |
-
"visual.blocks.0.mlp.up_proj",
|
60 |
-
"visual.blocks.0.mlp.down_proj",
|
61 |
-
"visual.blocks.1.attn.qkv",
|
62 |
-
"visual.blocks.1.attn.proj",
|
63 |
-
"visual.blocks.1.mlp.gate_proj",
|
64 |
-
"visual.blocks.1.mlp.up_proj",
|
65 |
-
"visual.blocks.1.mlp.down_proj",
|
66 |
-
"visual.blocks.2.attn.qkv",
|
67 |
-
"visual.blocks.2.attn.proj",
|
68 |
-
"visual.blocks.2.mlp.gate_proj",
|
69 |
-
"visual.blocks.2.mlp.up_proj",
|
70 |
-
"visual.blocks.2.mlp.down_proj",
|
71 |
-
"visual.blocks.3.attn.qkv",
|
72 |
-
"visual.blocks.3.attn.proj",
|
73 |
-
"visual.blocks.3.mlp.gate_proj",
|
74 |
-
"visual.blocks.3.mlp.up_proj",
|
75 |
-
"visual.blocks.3.mlp.down_proj",
|
76 |
-
"visual.blocks.4.attn.qkv",
|
77 |
-
"visual.blocks.4.attn.proj",
|
78 |
-
"visual.blocks.4.mlp.gate_proj",
|
79 |
-
"visual.blocks.4.mlp.up_proj",
|
80 |
-
"visual.blocks.4.mlp.down_proj",
|
81 |
-
"visual.blocks.5.attn.qkv",
|
82 |
-
"visual.blocks.5.attn.proj",
|
83 |
-
"visual.blocks.5.mlp.gate_proj",
|
84 |
-
"visual.blocks.5.mlp.up_proj",
|
85 |
-
"visual.blocks.5.mlp.down_proj",
|
86 |
-
"visual.blocks.6.attn.qkv",
|
87 |
-
"visual.blocks.6.attn.proj",
|
88 |
-
"visual.blocks.6.mlp.gate_proj",
|
89 |
-
"visual.blocks.6.mlp.up_proj",
|
90 |
-
"visual.blocks.6.mlp.down_proj",
|
91 |
-
"visual.blocks.7.attn.qkv",
|
92 |
-
"visual.blocks.7.attn.proj",
|
93 |
-
"visual.blocks.7.mlp.gate_proj",
|
94 |
-
"visual.blocks.7.mlp.up_proj",
|
95 |
-
"visual.blocks.7.mlp.down_proj",
|
96 |
-
"visual.blocks.8.attn.qkv",
|
97 |
-
"visual.blocks.8.attn.proj",
|
98 |
-
"visual.blocks.8.mlp.gate_proj",
|
99 |
-
"visual.blocks.8.mlp.up_proj",
|
100 |
-
"visual.blocks.8.mlp.down_proj",
|
101 |
-
"visual.blocks.9.attn.qkv",
|
102 |
-
"visual.blocks.9.attn.proj",
|
103 |
-
"visual.blocks.9.mlp.gate_proj",
|
104 |
-
"visual.blocks.9.mlp.up_proj",
|
105 |
-
"visual.blocks.9.mlp.down_proj",
|
106 |
-
"visual.blocks.10.attn.qkv",
|
107 |
-
"visual.blocks.10.attn.proj",
|
108 |
-
"visual.blocks.10.mlp.gate_proj",
|
109 |
-
"visual.blocks.10.mlp.up_proj",
|
110 |
-
"visual.blocks.10.mlp.down_proj",
|
111 |
-
"visual.blocks.11.attn.qkv",
|
112 |
-
"visual.blocks.11.attn.proj",
|
113 |
-
"visual.blocks.11.mlp.gate_proj",
|
114 |
-
"visual.blocks.11.mlp.up_proj",
|
115 |
-
"visual.blocks.11.mlp.down_proj",
|
116 |
-
"visual.blocks.12.attn.qkv",
|
117 |
-
"visual.blocks.12.attn.proj",
|
118 |
-
"visual.blocks.12.mlp.gate_proj",
|
119 |
-
"visual.blocks.12.mlp.up_proj",
|
120 |
-
"visual.blocks.12.mlp.down_proj",
|
121 |
-
"visual.blocks.13.attn.qkv",
|
122 |
-
"visual.blocks.13.attn.proj",
|
123 |
-
"visual.blocks.13.mlp.gate_proj",
|
124 |
-
"visual.blocks.13.mlp.up_proj",
|
125 |
-
"visual.blocks.13.mlp.down_proj",
|
126 |
-
"visual.blocks.14.attn.qkv",
|
127 |
-
"visual.blocks.14.attn.proj",
|
128 |
-
"visual.blocks.14.mlp.gate_proj",
|
129 |
-
"visual.blocks.14.mlp.up_proj",
|
130 |
-
"visual.blocks.14.mlp.down_proj",
|
131 |
-
"visual.blocks.15.attn.qkv",
|
132 |
-
"visual.blocks.15.attn.proj",
|
133 |
-
"visual.blocks.15.mlp.gate_proj",
|
134 |
-
"visual.blocks.15.mlp.up_proj",
|
135 |
-
"visual.blocks.15.mlp.down_proj",
|
136 |
-
"visual.blocks.16.attn.qkv",
|
137 |
-
"visual.blocks.16.attn.proj",
|
138 |
-
"visual.blocks.16.mlp.gate_proj",
|
139 |
-
"visual.blocks.16.mlp.up_proj",
|
140 |
-
"visual.blocks.16.mlp.down_proj",
|
141 |
-
"visual.blocks.17.attn.qkv",
|
142 |
-
"visual.blocks.17.attn.proj",
|
143 |
-
"visual.blocks.17.mlp.gate_proj",
|
144 |
-
"visual.blocks.17.mlp.up_proj",
|
145 |
-
"visual.blocks.17.mlp.down_proj",
|
146 |
-
"visual.blocks.18.attn.qkv",
|
147 |
-
"visual.blocks.18.attn.proj",
|
148 |
-
"visual.blocks.18.mlp.gate_proj",
|
149 |
-
"visual.blocks.18.mlp.up_proj",
|
150 |
-
"visual.blocks.18.mlp.down_proj",
|
151 |
-
"visual.blocks.19.attn.qkv",
|
152 |
-
"visual.blocks.19.attn.proj",
|
153 |
-
"visual.blocks.19.mlp.gate_proj",
|
154 |
-
"visual.blocks.19.mlp.up_proj",
|
155 |
-
"visual.blocks.19.mlp.down_proj",
|
156 |
-
"visual.blocks.20.attn.qkv",
|
157 |
-
"visual.blocks.20.attn.proj",
|
158 |
-
"visual.blocks.20.mlp.gate_proj",
|
159 |
-
"visual.blocks.20.mlp.up_proj",
|
160 |
-
"visual.blocks.20.mlp.down_proj",
|
161 |
-
"visual.blocks.21.attn.qkv",
|
162 |
-
"visual.blocks.21.attn.proj",
|
163 |
-
"visual.blocks.21.mlp.gate_proj",
|
164 |
-
"visual.blocks.21.mlp.up_proj",
|
165 |
-
"visual.blocks.21.mlp.down_proj",
|
166 |
-
"visual.blocks.22.attn.qkv",
|
167 |
-
"visual.blocks.22.attn.proj",
|
168 |
-
"visual.blocks.22.mlp.gate_proj",
|
169 |
-
"visual.blocks.22.mlp.up_proj",
|
170 |
-
"visual.blocks.22.mlp.down_proj",
|
171 |
-
"visual.blocks.23.attn.qkv",
|
172 |
-
"visual.blocks.23.attn.proj",
|
173 |
-
"visual.blocks.23.mlp.gate_proj",
|
174 |
-
"visual.blocks.23.mlp.up_proj",
|
175 |
-
"visual.blocks.23.mlp.down_proj",
|
176 |
-
"visual.blocks.24.attn.qkv",
|
177 |
-
"visual.blocks.24.attn.proj",
|
178 |
-
"visual.blocks.24.mlp.gate_proj",
|
179 |
-
"visual.blocks.24.mlp.up_proj",
|
180 |
-
"visual.blocks.24.mlp.down_proj",
|
181 |
-
"visual.blocks.25.attn.qkv",
|
182 |
-
"visual.blocks.25.attn.proj",
|
183 |
-
"visual.blocks.25.mlp.gate_proj",
|
184 |
-
"visual.blocks.25.mlp.up_proj",
|
185 |
-
"visual.blocks.25.mlp.down_proj",
|
186 |
-
"visual.blocks.26.attn.qkv",
|
187 |
-
"visual.blocks.26.attn.proj",
|
188 |
-
"visual.blocks.26.mlp.gate_proj",
|
189 |
-
"visual.blocks.26.mlp.up_proj",
|
190 |
-
"visual.blocks.26.mlp.down_proj",
|
191 |
-
"visual.blocks.27.attn.qkv",
|
192 |
-
"visual.blocks.27.attn.proj",
|
193 |
-
"visual.blocks.27.mlp.gate_proj",
|
194 |
-
"visual.blocks.27.mlp.up_proj",
|
195 |
-
"visual.blocks.27.mlp.down_proj",
|
196 |
-
"visual.blocks.28.attn.qkv",
|
197 |
-
"visual.blocks.28.attn.proj",
|
198 |
-
"visual.blocks.28.mlp.gate_proj",
|
199 |
-
"visual.blocks.28.mlp.up_proj",
|
200 |
-
"visual.blocks.28.mlp.down_proj",
|
201 |
-
"visual.blocks.29.attn.qkv",
|
202 |
-
"visual.blocks.29.attn.proj",
|
203 |
-
"visual.blocks.29.mlp.gate_proj",
|
204 |
-
"visual.blocks.29.mlp.up_proj",
|
205 |
-
"visual.blocks.29.mlp.down_proj",
|
206 |
-
"visual.blocks.30.attn.qkv",
|
207 |
-
"visual.blocks.30.attn.proj",
|
208 |
-
"visual.blocks.30.mlp.gate_proj",
|
209 |
-
"visual.blocks.30.mlp.up_proj",
|
210 |
-
"visual.blocks.30.mlp.down_proj",
|
211 |
-
"visual.blocks.31.attn.qkv",
|
212 |
-
"visual.blocks.31.attn.proj",
|
213 |
-
"visual.blocks.31.mlp.gate_proj",
|
214 |
-
"visual.blocks.31.mlp.up_proj",
|
215 |
-
"visual.blocks.31.mlp.down_proj",
|
216 |
-
"visual.merger.mlp.0",
|
217 |
-
"visual.merger.mlp.2",
|
218 |
-
"lm_head"
|
219 |
-
],
|
220 |
-
"kv_cache_scheme": null,
|
221 |
-
"quant_method": "compressed-tensors",
|
222 |
-
"quantization_status": "compressed"
|
223 |
-
},
|
224 |
"rms_norm_eps": 1e-06,
|
225 |
-
"rope_scaling": {
|
226 |
-
"mrope_section": [
|
227 |
-
16,
|
228 |
-
24,
|
229 |
-
24
|
230 |
-
],
|
231 |
-
"rope_type": "default",
|
232 |
-
"type": "default"
|
233 |
-
},
|
234 |
"rope_theta": 1000000.0,
|
235 |
"sliding_window": 32768,
|
236 |
"tie_word_embeddings": false,
|
237 |
"torch_dtype": "bfloat16",
|
238 |
-
"transformers_version": "4.
|
239 |
"use_cache": true,
|
240 |
"use_sliding_window": false,
|
241 |
-
"video_token_id": 151656,
|
242 |
"vision_config": {
|
|
|
|
|
243 |
"hidden_size": 1280,
|
244 |
-
"in_chans": 3,
|
245 |
"intermediate_size": 3456,
|
246 |
-
"
|
|
|
247 |
"out_hidden_size": 8192,
|
|
|
|
|
248 |
"spatial_patch_size": 14,
|
249 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
250 |
},
|
251 |
-
"vision_end_token_id": 151653,
|
252 |
-
"vision_start_token_id": 151652,
|
253 |
-
"vision_token_id": 151654,
|
254 |
"vocab_size": 152064
|
255 |
}
|
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"Qwen2_5_VLForConditionalGeneration"
|
4 |
],
|
5 |
"attention_dropout": 0.0,
|
6 |
"bos_token_id": 151643,
|
7 |
"eos_token_id": 151645,
|
8 |
+
"vision_start_token_id": 151652,
|
9 |
+
"vision_end_token_id": 151653,
|
10 |
+
"vision_token_id": 151654,
|
11 |
+
"image_token_id": 151655,
|
12 |
+
"video_token_id": 151656,
|
13 |
"hidden_act": "silu",
|
14 |
"hidden_size": 8192,
|
|
|
15 |
"initializer_range": 0.02,
|
16 |
"intermediate_size": 29568,
|
17 |
"max_position_embeddings": 128000,
|
|
|
20 |
"num_attention_heads": 64,
|
21 |
"num_hidden_layers": 80,
|
22 |
"num_key_value_heads": 8,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
"rms_norm_eps": 1e-06,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
"rope_theta": 1000000.0,
|
25 |
"sliding_window": 32768,
|
26 |
"tie_word_embeddings": false,
|
27 |
"torch_dtype": "bfloat16",
|
28 |
+
"transformers_version": "4.41.2",
|
29 |
"use_cache": true,
|
30 |
"use_sliding_window": false,
|
|
|
31 |
"vision_config": {
|
32 |
+
"depth": 32,
|
33 |
+
"hidden_act": "silu",
|
34 |
"hidden_size": 1280,
|
|
|
35 |
"intermediate_size": 3456,
|
36 |
+
"num_heads": 16,
|
37 |
+
"in_chans": 3,
|
38 |
"out_hidden_size": 8192,
|
39 |
+
"patch_size": 14,
|
40 |
+
"spatial_merge_size": 2,
|
41 |
"spatial_patch_size": 14,
|
42 |
+
"window_size": 112,
|
43 |
+
"fullatt_block_indexes": [
|
44 |
+
7,
|
45 |
+
15,
|
46 |
+
23,
|
47 |
+
31
|
48 |
+
],
|
49 |
+
"tokens_per_second": 2,
|
50 |
+
"temporal_patch_size": 2
|
51 |
+
},
|
52 |
+
"rope_scaling": {
|
53 |
+
"type": "mrope",
|
54 |
+
"mrope_section": [
|
55 |
+
16,
|
56 |
+
24,
|
57 |
+
24
|
58 |
+
]
|
59 |
},
|
|
|
|
|
|
|
60 |
"vocab_size": 152064
|
61 |
}
|
generation_config.json
CHANGED
@@ -1,13 +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 |
-
"
|
11 |
-
"
|
12 |
-
|
13 |
-
}
|
|
|
1 |
{
|
2 |
"bos_token_id": 151643,
|
3 |
+
"pad_token_id": 151643,
|
4 |
"do_sample": true,
|
5 |
"eos_token_id": [
|
6 |
151645,
|
7 |
151643
|
8 |
],
|
|
|
9 |
"repetition_penalty": 1.05,
|
10 |
+
"temperature": 0.000001,
|
11 |
+
"transformers_version": "4.49.0"
|
12 |
+
}
|
|
merges.txt
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
#version: 0.2
|
2 |
Ġ Ġ
|
3 |
ĠĠ ĠĠ
|
4 |
i n
|
|
|
|
|
1 |
Ġ Ġ
|
2 |
ĠĠ ĠĠ
|
3 |
i n
|
preprocessor_config.json
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
|
|
6 |
"image_mean": [
|
7 |
0.48145466,
|
8 |
0.4578275,
|
@@ -13,17 +14,6 @@
|
|
13 |
0.26130258,
|
14 |
0.27577711
|
15 |
],
|
16 |
-
"max_pixels": 12845056,
|
17 |
-
"merge_size": 2,
|
18 |
-
"min_pixels": 3136,
|
19 |
-
"patch_size": 14,
|
20 |
"image_processor_type": "Qwen2VLImageProcessor",
|
21 |
-
"processor_class": "Qwen2_5_VLProcessor"
|
22 |
-
|
23 |
-
"rescale_factor": 0.00392156862745098,
|
24 |
-
"size": {
|
25 |
-
"longest_edge": 12845056,
|
26 |
-
"shortest_edge": 3136
|
27 |
-
},
|
28 |
-
"temporal_patch_size": 2
|
29 |
-
}
|
|
|
1 |
{
|
2 |
+
"min_pixels": 3136,
|
3 |
+
"max_pixels": 12845056,
|
4 |
+
"patch_size": 14,
|
5 |
+
"temporal_patch_size": 2,
|
6 |
+
"merge_size": 2,
|
7 |
"image_mean": [
|
8 |
0.48145466,
|
9 |
0.4578275,
|
|
|
14 |
0.26130258,
|
15 |
0.27577711
|
16 |
],
|
|
|
|
|
|
|
|
|
17 |
"image_processor_type": "Qwen2VLImageProcessor",
|
18 |
+
"processor_class": "Qwen2_5_VLProcessor"
|
19 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
special_tokens_map.json
DELETED
@@ -1,31 +0,0 @@
|
|
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
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539
|
3 |
+
size 7031645
|
tokenizer_config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_bos_token": false,
|
3 |
"add_prefix_space": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"151643": {
|
@@ -195,15 +194,14 @@
|
|
195 |
"<|video_pad|>"
|
196 |
],
|
197 |
"bos_token": null,
|
198 |
-
"chat_template": "{
|
199 |
"clean_up_tokenization_spaces": false,
|
200 |
"eos_token": "<|im_end|>",
|
201 |
"errors": "replace",
|
202 |
-
"extra_special_tokens": {},
|
203 |
"model_max_length": 131072,
|
204 |
"pad_token": "<|endoftext|>",
|
205 |
-
"processor_class": "Qwen2_5_VLProcessor",
|
206 |
"split_special_tokens": false,
|
207 |
"tokenizer_class": "Qwen2Tokenizer",
|
208 |
-
"unk_token": null
|
|
|
209 |
}
|
|
|
1 |
{
|
|
|
2 |
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
"151643": {
|
|
|
194 |
"<|video_pad|>"
|
195 |
],
|
196 |
"bos_token": null,
|
197 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
198 |
"clean_up_tokenization_spaces": false,
|
199 |
"eos_token": "<|im_end|>",
|
200 |
"errors": "replace",
|
|
|
201 |
"model_max_length": 131072,
|
202 |
"pad_token": "<|endoftext|>",
|
|
|
203 |
"split_special_tokens": false,
|
204 |
"tokenizer_class": "Qwen2Tokenizer",
|
205 |
+
"unk_token": null,
|
206 |
+
"add_bos_token": false
|
207 |
}
|