PyTorch
English
Tevatron
phi3_v
vidore
custom_code
MrLight commited on
Commit
2081611
1 Parent(s): 65f7e6e

Upload processor

Browse files
README.md CHANGED
@@ -1,13 +1,13 @@
1
  ---
2
- license: mit
3
  language:
4
  - en
 
 
5
  tags:
6
  - vidore
7
  datasets:
8
  - Tevatron/docmatix-ir
9
  - HuggingFaceM4/Docmatix
10
- library_name: Tevatron
11
  ---
12
 
13
  # DSE-Phi3-Docmatix-V1.0
 
1
  ---
 
2
  language:
3
  - en
4
+ license: mit
5
+ library_name: Tevatron
6
  tags:
7
  - vidore
8
  datasets:
9
  - Tevatron/docmatix-ir
10
  - HuggingFaceM4/Docmatix
 
11
  ---
12
 
13
  # DSE-Phi3-Docmatix-V1.0
preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoImageProcessor": "microsoft/Phi-3-vision-128k-instruct--image_processing_phi3_v.Phi3VImageProcessor",
4
+ "AutoProcessor": "microsoft/Phi-3-vision-128k-instruct--processing_phi3_v.Phi3VProcessor"
5
+ },
6
+ "do_convert_rgb": true,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_processor_type": "Phi3VImageProcessor",
13
+ "image_std": [
14
+ 0.26862954,
15
+ 0.26130258,
16
+ 0.27577711
17
+ ],
18
+ "num_crops": 16,
19
+ "num_img_tokens": 144,
20
+ "processor_class": "Phi3VProcessor"
21
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|system|>",
4
+ "<|end|>",
5
+ "<|user|>",
6
+ "<|end|>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "<|endoftext|>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "unk_token": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,409 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|placeholder1|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|placeholder2|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|placeholder3|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|placeholder4|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|placeholder5|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|placeholder6|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32011": {
118
+ "content": "<|placeholder7|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": true,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "32012": {
126
+ "content": "<|placeholder8|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": true,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "32013": {
134
+ "content": "<|placeholder9|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": true,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "32014": {
142
+ "content": "<|placeholder10|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": true,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "32015": {
150
+ "content": "<|placeholder11|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": true,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "32016": {
158
+ "content": "<|placeholder12|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": true,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "32017": {
166
+ "content": "<|placeholder13|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": true,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "32018": {
174
+ "content": "<|placeholder14|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": true,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "32019": {
182
+ "content": "<|placeholder15|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": true,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "32020": {
190
+ "content": "<|placeholder16|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": true,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "32021": {
198
+ "content": "<|placeholder17|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": true,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "32022": {
206
+ "content": "<|placeholder18|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": true,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "32023": {
214
+ "content": "<|placeholder19|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": true,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "32024": {
222
+ "content": "<|placeholder20|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": true,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "32025": {
230
+ "content": "<|placeholder21|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": true,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "32026": {
238
+ "content": "<|placeholder22|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": true,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "32027": {
246
+ "content": "<|placeholder23|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": true,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "32028": {
254
+ "content": "<|placeholder24|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": true,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "32029": {
262
+ "content": "<|placeholder25|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": true,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "32030": {
270
+ "content": "<|placeholder26|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": true,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "32031": {
278
+ "content": "<|placeholder27|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": true,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "32032": {
286
+ "content": "<|placeholder28|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": true,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "32033": {
294
+ "content": "<|placeholder29|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": true,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "32034": {
302
+ "content": "<|placeholder30|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": true,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "32035": {
310
+ "content": "<|placeholder31|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": true,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "32036": {
318
+ "content": "<|placeholder32|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": true,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "32037": {
326
+ "content": "<|placeholder33|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": true,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "32038": {
334
+ "content": "<|placeholder34|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": true,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "32039": {
342
+ "content": "<|placeholder35|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": true,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "32040": {
350
+ "content": "<|placeholder36|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": true,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "32041": {
358
+ "content": "<|placeholder37|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": true,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "32042": {
366
+ "content": "<|placeholder38|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": true,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "32043": {
374
+ "content": "<|placeholder39|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": true,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "32044": {
382
+ "content": "<|image|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": true,
386
+ "single_word": false,
387
+ "special": true
388
+ }
389
+ },
390
+ "additional_special_tokens": [
391
+ "<|system|>",
392
+ "<|end|>",
393
+ "<|user|>",
394
+ "<|end|>"
395
+ ],
396
+ "bos_token": "<s>",
397
+ "chat_template": "{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{- '<|assistant|>\n' -}}{% endif %}",
398
+ "clean_up_tokenization_spaces": false,
399
+ "eos_token": "<|endoftext|>",
400
+ "legacy": false,
401
+ "model_max_length": 131072,
402
+ "pad_token": "<|endoftext|>",
403
+ "padding_side": "right",
404
+ "processor_class": "Phi3VProcessor",
405
+ "sp_model_kwargs": {},
406
+ "tokenizer_class": "LlamaTokenizer",
407
+ "unk_token": "<unk>",
408
+ "use_default_system_prompt": false
409
+ }