Hugging Face's logo

kingsley01
/
InternVL2_5-1B-MPO-hf

Image-Text-to-Text
Transformers
Safetensors
multilingual
internvl
text2text-generation
custom_code
conversational
Inference Endpoints
Model card Files Community
kingsley01 commited on
Commit
538970b
·
verified ·
1 Parent(s): 0abc5a5

Upload tokenizer

Browse files
Files changed (8) hide show
  1. .gitattributes +1 -0
  2. README.md +5 -5
  3. added_tokens.json +33 -0
  4. merges.txt +0 -0
  5. special_tokens_map.json +94 -0
  6. tokenizer.json +3 -0
  7. tokenizer_config.json +290 -0
  8. 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 CHANGED
@@ -3,15 +3,15 @@ license: mit
3
  pipeline_tag: image-text-to-text
4
  library_name: transformers
5
  base_model:
6
- - OpenGVLab/InternVL2_5-1B
7
  base_model_relation: finetune
8
  datasets:
9
- - OpenGVLab/MMPR-v1.1
10
  language:
11
- - multilingual
12
  tags:
13
- - internvl
14
- - custom_code
15
  ---
16
 
17
  # InternVL2_5-1B-MPO
 
3
  pipeline_tag: image-text-to-text
4
  library_name: transformers
5
  base_model:
6
+ - OpenGVLab/InternVL2_5-1B
7
  base_model_relation: finetune
8
  datasets:
9
+ - OpenGVLab/MMPR-v1.1
10
  language:
11
+ - multilingual
12
  tags:
13
+ - internvl
14
+ - custom_code
15
  ---
16
 
17
  # InternVL2_5-1B-MPO
added_tokens.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 151673,
3
+ "</img>": 151666,
4
+ "</quad>": 151669,
5
+ "</ref>": 151671,
6
+ "</tool_call>": 151658,
7
+ "<IMG_CONTEXT>": 151667,
8
+ "<box>": 151672,
9
+ "<img>": 151665,
10
+ "<quad>": 151668,
11
+ "<ref>": 151670,
12
+ "<tool_call>": 151657,
13
+ "<|box_end|>": 151649,
14
+ "<|box_start|>": 151648,
15
+ "<|endoftext|>": 151643,
16
+ "<|file_sep|>": 151664,
17
+ "<|fim_middle|>": 151660,
18
+ "<|fim_pad|>": 151662,
19
+ "<|fim_prefix|>": 151659,
20
+ "<|fim_suffix|>": 151661,
21
+ "<|im_end|>": 151645,
22
+ "<|im_start|>": 151644,
23
+ "<|image_pad|>": 151655,
24
+ "<|object_ref_end|>": 151647,
25
+ "<|object_ref_start|>": 151646,
26
+ "<|quad_end|>": 151651,
27
+ "<|quad_start|>": 151650,
28
+ "<|repo_name|>": 151663,
29
+ "<|video_pad|>": 151656,
30
+ "<|vision_end|>": 151653,
31
+ "<|vision_pad|>": 151654,
32
+ "<|vision_start|>": 151652
33
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "content": "<img>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ {
24
+ "content": "</img>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ {
31
+ "content": "<IMG_CONTEXT>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ {
38
+ "content": "<quad>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ {
45
+ "content": "</quad>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ },
51
+ {
52
+ "content": "<ref>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false
57
+ },
58
+ {
59
+ "content": "</ref>",
60
+ "lstrip": false,
61
+ "normalized": false,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ },
65
+ {
66
+ "content": "<box>",
67
+ "lstrip": false,
68
+ "normalized": false,
69
+ "rstrip": false,
70
+ "single_word": false
71
+ },
72
+ {
73
+ "content": "</box>",
74
+ "lstrip": false,
75
+ "normalized": false,
76
+ "rstrip": false,
77
+ "single_word": false
78
+ }
79
+ ],
80
+ "eos_token": {
81
+ "content": "<|im_end|>",
82
+ "lstrip": false,
83
+ "normalized": false,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ "pad_token": {
88
+ "content": "<|endoftext|>",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ }
94
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f9ba4b4a6625b5047a1356f6081b641c3e4e6a4a198facbd4bef217747d1685
3
+ size 11423548
tokenizer_config.json ADDED
@@ -0,0 +1,290 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "151665": {
182
+ "content": "<img>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "</img>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<IMG_CONTEXT>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151668": {
206
+ "content": "<quad>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "151669": {
214
+ "content": "</quad>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<ref>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "</ref>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<box>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "</box>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ }
253
+ },
254
+ "additional_special_tokens": [
255
+ "<|im_start|>",
256
+ "<|im_end|>",
257
+ "<|object_ref_start|>",
258
+ "<|object_ref_end|>",
259
+ "<|box_start|>",
260
+ "<|box_end|>",
261
+ "<|quad_start|>",
262
+ "<|quad_end|>",
263
+ "<|vision_start|>",
264
+ "<|vision_end|>",
265
+ "<|vision_pad|>",
266
+ "<|image_pad|>",
267
+ "<|video_pad|>",
268
+ "<img>",
269
+ "</img>",
270
+ "<IMG_CONTEXT>",
271
+ "<quad>",
272
+ "</quad>",
273
+ "<ref>",
274
+ "</ref>",
275
+ "<box>",
276
+ "</box>"
277
+ ],
278
+ "bos_token": null,
279
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n'}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<image>\n' }}{% elif content['type'] == 'video' %}{{ '<video>\n' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>\n'}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant\n' }}{% endif %}",
280
+ "clean_up_tokenization_spaces": false,
281
+ "eos_token": "<|im_end|>",
282
+ "errors": "replace",
283
+ "extra_special_tokens": {},
284
+ "model_max_length": 8192,
285
+ "pad_token": "<|endoftext|>",
286
+ "return_token_type_ids": false,
287
+ "split_special_tokens": false,
288
+ "tokenizer_class": "Qwen2Tokenizer",
289
+ "unk_token": null
290
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff