Molbap HF Staff commited on
Commit
55c7178
·
verified ·
1 Parent(s): e56ef68

Upload processor

Browse files
added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<im_col>": 100281,
3
+ "<im_end>": 100279,
4
+ "<im_patch>": 100280,
5
+ "<im_start>": 100278,
6
+ "<image>": 100283,
7
+ "<|image|>": 100282
8
+ }
chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {{ bos_token or '' }}{% for message in messages %}{%- if (loop.index % 2 == 1 and message['role'] != 'user') or (loop.index % 2 == 0 and message['role'].lower() != 'assistant') -%}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{%- endif -%}{% if message['content'] is not string %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<image> ' }}{% endif %}{% endfor %}{% endif %}{{ message['role'].capitalize() + ': ' }}{% if message['content'] is string %}{{ message['content'] + ' ' }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'text' %}{{ content['text'] + ' ' }}{% endif %}{% endfor %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoImageProcessor": "image_preprocessing_molmo.MolmoImageProcessor",
4
+ "AutoProcessor": "preprocessing_molmo.MolmoProcessor"
5
+ },
6
+ "base_image_input_size": [
7
+ 336,
8
+ 336
9
+ ],
10
+ "crop_patches": 24,
11
+ "crop_size": 336,
12
+ "crop_window_patches": 16,
13
+ "crop_window_size": 224,
14
+ "data_format": "channels_first",
15
+ "default_to_square": true,
16
+ "device": "cuda:2",
17
+ "do_center_crop": null,
18
+ "do_convert_rgb": true,
19
+ "do_normalize": true,
20
+ "do_pad": true,
21
+ "do_rescale": true,
22
+ "do_resize": true,
23
+ "do_split_into_crops": true,
24
+ "image_column_token": "<im_col>",
25
+ "image_end_token": "<im_end>",
26
+ "image_mean": [
27
+ 0.48145466,
28
+ 0.4578275,
29
+ 0.40821073
30
+ ],
31
+ "image_padding_mask": true,
32
+ "image_patch_size": 14,
33
+ "image_patch_token": "<im_patch>",
34
+ "image_processor_type": "MolmoImageProcessorFast",
35
+ "image_start_token": "<im_start>",
36
+ "image_std": [
37
+ 0.26862954,
38
+ 0.26130258,
39
+ 0.27577711
40
+ ],
41
+ "image_token_length_h": 12,
42
+ "image_token_length_w": 12,
43
+ "input_data_format": null,
44
+ "max_crops": 12,
45
+ "max_num_crops": 12,
46
+ "overlap_margins": [
47
+ 4,
48
+ 4
49
+ ],
50
+ "padding_mode": "constant",
51
+ "padding_value": 1.0,
52
+ "patches_per_image_height": 24,
53
+ "patches_per_image_width": 24,
54
+ "processor_class": "MolmoProcessor",
55
+ "resample": 2,
56
+ "rescale_factor": 0.00392156862745098,
57
+ "return_tensors": null,
58
+ "size": {
59
+ "height": 336,
60
+ "width": 336
61
+ },
62
+ "tokens_per_image": 144,
63
+ "tokens_per_image_height": 12,
64
+ "tokens_per_image_width": 12,
65
+ "total_margin_pixels": 112
66
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<im_start>",
4
+ "<im_end>",
5
+ "<im_patch>",
6
+ "<im_col>",
7
+ "<|image|>"
8
+ ],
9
+ "boi_token": "<im_start>",
10
+ "bos_token": {
11
+ "content": "<|endoftext|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "eoi_token": "<im_end>",
18
+ "eos_token": {
19
+ "content": "<|endoftext|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "im_col_token": "<im_col>",
26
+ "im_patch_token": "<im_patch>",
27
+ "image_token": "<image>",
28
+ "pad_token": {
29
+ "content": "<|pad|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "unk_token": {
36
+ "content": "<|endoftext|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ }
42
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,260 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "100256": {
5
+ "content": "<|extra_id_0|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": false
11
+ },
12
+ "100257": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "100258": {
21
+ "content": "<|fim_prefix|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "100259": {
29
+ "content": "<|fim_middle|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "100260": {
37
+ "content": "<|fim_suffix|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "100261": {
45
+ "content": "|||PHONE_NUMBER|||",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "100262": {
53
+ "content": "|||EMAIL_ADDRESS|||",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "100263": {
61
+ "content": "|||IP_ADDRESS|||",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "100264": {
69
+ "content": "<|im_start|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "100265": {
77
+ "content": "<|im_end|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "100266": {
85
+ "content": "<|extra_id_1|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "100267": {
93
+ "content": "<|extra_id_2|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "100268": {
101
+ "content": "<|extra_id_3|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "100269": {
109
+ "content": "<|extra_id_4|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "100270": {
117
+ "content": "<|extra_id_5|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "100271": {
125
+ "content": "<|extra_id_6|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "100272": {
133
+ "content": "<|extra_id_7|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "100273": {
141
+ "content": "<|extra_id_8|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "100274": {
149
+ "content": "<|extra_id_9|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "100275": {
157
+ "content": "<|extra_id_10|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "100276": {
165
+ "content": "<|endofprompt|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "100277": {
173
+ "content": "<|pad|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "100278": {
181
+ "content": "<im_start>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "100279": {
189
+ "content": "<im_end>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "100280": {
197
+ "content": "<im_patch>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "100281": {
205
+ "content": "<im_col>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "100282": {
213
+ "content": "<|image|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "100283": {
221
+ "content": "<image>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ }
228
+ },
229
+ "additional_special_tokens": [
230
+ "<im_start>",
231
+ "<im_end>",
232
+ "<im_patch>",
233
+ "<im_col>",
234
+ "<|image|>"
235
+ ],
236
+ "auto_map": {
237
+ "AutoProcessor": "preprocessing_molmo.MolmoProcessor"
238
+ },
239
+ "boi_token": "<im_start>",
240
+ "bos_token": "<|endoftext|>",
241
+ "clean_up_tokenization_spaces": false,
242
+ "device": "cuda:2",
243
+ "eoi_token": "<im_end>",
244
+ "eos_token": "<|endoftext|>",
245
+ "extra_special_tokens": {
246
+ "boi_token": "<im_start>",
247
+ "eoi_token": "<im_end>",
248
+ "im_col_token": "<im_col>",
249
+ "im_patch_token": "<im_patch>",
250
+ "image_token": "<image>"
251
+ },
252
+ "im_col_token": "<im_col>",
253
+ "im_patch_token": "<im_patch>",
254
+ "image_token": "<image>",
255
+ "model_max_length": 8192,
256
+ "pad_token": "<|pad|>",
257
+ "processor_class": "MolmoProcessor",
258
+ "tokenizer_class": "GPT2Tokenizer",
259
+ "unk_token": "<|endoftext|>"
260
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff