Kim-Rass commited on
Commit
8121ff2
·
verified ·
1 Parent(s): 946038d

Upload processor

Browse files
.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 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 151673,
3
+ "</caption>": 151729,
4
+ "</chart>": 151785,
5
+ "</checkbox_selected>": 151748,
6
+ "</checkbox_unselected>": 151750,
7
+ "</doctag>": 151767,
8
+ "</footnote>": 151732,
9
+ "</form>": 151752,
10
+ "</formula>": 151734,
11
+ "</group>": 151765,
12
+ "</img>": 151666,
13
+ "</key_": 151780,
14
+ "</key_value_region>": 151754,
15
+ "</list_item>": 151736,
16
+ "</ordered_list>": 151761,
17
+ "</otsl>": 151746,
18
+ "</page_footer>": 151738,
19
+ "</page_header>": 151740,
20
+ "</paragraph>": 151757,
21
+ "</picture>": 151742,
22
+ "</quad>": 151669,
23
+ "</ref>": 151671,
24
+ "</reference>": 151759,
25
+ "</section_header_level_": 151744,
26
+ "</smiles>": 151788,
27
+ "</tool_call>": 151658,
28
+ "</unordered_list>": 151763,
29
+ "</value_": 151782,
30
+ "<IMG_CONTEXT>": 151667,
31
+ "<box>": 151672,
32
+ "<caption>": 151728,
33
+ "<chart>": 151784,
34
+ "<checkbox_selected>": 151747,
35
+ "<checkbox_unselected>": 151749,
36
+ "<ched>": 151776,
37
+ "<doctag>": 151766,
38
+ "<ecel>": 151771,
39
+ "<empty_output>": 151688,
40
+ "<end_of_utterance>": 151816,
41
+ "<fake_token_around_image>": 151726,
42
+ "<fcel>": 151770,
43
+ "<file_sep>": 151677,
44
+ "<filename>": 151678,
45
+ "<footnote>": 151730,
46
+ "<form>": 151751,
47
+ "<formula>": 151733,
48
+ "<gh_stars>": 151679,
49
+ "<global-img>": 151689,
50
+ "<group>": 151764,
51
+ "<image>": 151727,
52
+ "<img>": 151665,
53
+ "<issue_closed>": 151682,
54
+ "<issue_comment>": 151681,
55
+ "<issue_start>": 151680,
56
+ "<jupyter_code>": 151685,
57
+ "<jupyter_output>": 151686,
58
+ "<jupyter_script>": 151687,
59
+ "<jupyter_start>": 151683,
60
+ "<jupyter_text>": 151684,
61
+ "<key_": 151779,
62
+ "<key_value_region>": 151753,
63
+ "<lcel>": 151772,
64
+ "<link_": 151783,
65
+ "<list_item>": 151735,
66
+ "<loc_": 151755,
67
+ "<nl>": 151775,
68
+ "<ordered_list>": 151760,
69
+ "<otsl>": 151745,
70
+ "<page_": 151768,
71
+ "<page_break>": 151786,
72
+ "<page_footer>": 151737,
73
+ "<page_header>": 151739,
74
+ "<paragraph>": 151756,
75
+ "<picture>": 151741,
76
+ "<quad>": 151668,
77
+ "<ref>": 151670,
78
+ "<reference>": 151758,
79
+ "<repo_name>": 151675,
80
+ "<reponame>": 151676,
81
+ "<rhed>": 151777,
82
+ "<row_1_col_1>": 151690,
83
+ "<row_1_col_2>": 151691,
84
+ "<row_1_col_3>": 151692,
85
+ "<row_1_col_4>": 151693,
86
+ "<row_1_col_5>": 151694,
87
+ "<row_1_col_6>": 151695,
88
+ "<row_2_col_1>": 151696,
89
+ "<row_2_col_2>": 151697,
90
+ "<row_2_col_3>": 151698,
91
+ "<row_2_col_4>": 151699,
92
+ "<row_2_col_5>": 151700,
93
+ "<row_2_col_6>": 151701,
94
+ "<row_3_col_1>": 151702,
95
+ "<row_3_col_2>": 151703,
96
+ "<row_3_col_3>": 151704,
97
+ "<row_3_col_4>": 151705,
98
+ "<row_3_col_5>": 151706,
99
+ "<row_3_col_6>": 151707,
100
+ "<row_4_col_1>": 151708,
101
+ "<row_4_col_2>": 151709,
102
+ "<row_4_col_3>": 151710,
103
+ "<row_4_col_4>": 151711,
104
+ "<row_4_col_5>": 151712,
105
+ "<row_4_col_6>": 151713,
106
+ "<row_5_col_1>": 151714,
107
+ "<row_5_col_2>": 151715,
108
+ "<row_5_col_3>": 151716,
109
+ "<row_5_col_4>": 151717,
110
+ "<row_5_col_5>": 151718,
111
+ "<row_5_col_6>": 151719,
112
+ "<row_6_col_1>": 151720,
113
+ "<row_6_col_2>": 151721,
114
+ "<row_6_col_3>": 151722,
115
+ "<row_6_col_4>": 151723,
116
+ "<row_6_col_5>": 151724,
117
+ "<row_6_col_6>": 151725,
118
+ "<section_header_level_": 151743,
119
+ "<smiles>": 151787,
120
+ "<text_break>": 151769,
121
+ "<tool_call>": 151657,
122
+ "<ucel>": 151773,
123
+ "<unordered_list>": 151762,
124
+ "<value_": 151781,
125
+ "<video>": 151674,
126
+ "<xcel>": 151774,
127
+ "<|bbox|>": 151818,
128
+ "<|box_end|>": 151649,
129
+ "<|box_start|>": 151648,
130
+ "<|endoftext|>": 151643,
131
+ "<|file_sep|>": 151664,
132
+ "<|fim_middle|>": 151660,
133
+ "<|fim_pad|>": 151662,
134
+ "<|fim_prefix|>": 151659,
135
+ "<|fim_suffix|>": 151661,
136
+ "<|im_end|>": 151645,
137
+ "<|im_start|>": 151644,
138
+ "<|image_pad|>": 151655,
139
+ "<|object_ref_end|>": 151647,
140
+ "<|object_ref_start|>": 151646,
141
+ "<|quad_end|>": 151651,
142
+ "<|quad_start|>": 151650,
143
+ "<|repo_name|>": 151663,
144
+ "<|reserved_special_token_3|>": 151731,
145
+ "<|reserved_special_token_50|>": 151778,
146
+ "<|reserved_special_token_61|>": 151789,
147
+ "<|reserved_special_token_62|>": 151790,
148
+ "<|reserved_special_token_63|>": 151791,
149
+ "<|reserved_special_token_64|>": 151792,
150
+ "<|reserved_special_token_65|>": 151793,
151
+ "<|reserved_special_token_66|>": 151794,
152
+ "<|reserved_special_token_67|>": 151795,
153
+ "<|reserved_special_token_68|>": 151796,
154
+ "<|reserved_special_token_69|>": 151797,
155
+ "<|reserved_special_token_70|>": 151798,
156
+ "<|reserved_special_token_71|>": 151799,
157
+ "<|reserved_special_token_72|>": 151800,
158
+ "<|reserved_special_token_73|>": 151801,
159
+ "<|reserved_special_token_74|>": 151802,
160
+ "<|reserved_special_token_75|>": 151803,
161
+ "<|reserved_special_token_76|>": 151804,
162
+ "<|reserved_special_token_77|>": 151805,
163
+ "<|reserved_special_token_78|>": 151806,
164
+ "<|reserved_special_token_79|>": 151807,
165
+ "<|reserved_special_token_80|>": 151808,
166
+ "<|reserved_special_token_81|>": 151809,
167
+ "<|reserved_special_token_82|>": 151810,
168
+ "<|reserved_special_token_83|>": 151811,
169
+ "<|reserved_special_token_84|>": 151812,
170
+ "<|reserved_special_token_85|>": 151813,
171
+ "<|reserved_special_token_86|>": 151814,
172
+ "<|reserved_special_token_87|>": 151815,
173
+ "<|value|>": 151817,
174
+ "<|video_pad|>": 151656,
175
+ "<|vision_end|>": 151653,
176
+ "<|vision_pad|>": 151654,
177
+ "<|vision_start|>": 151652
178
+ }
chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ '}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<IMG_CONTEXT>
3
+ ' }}{% elif content['type'] == 'video' %}{{ '<video>
4
+ ' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
6
+ ' }}{% endif %}
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "crop_to_patches": false,
4
+ "data_format": "channels_first",
5
+ "default_to_square": true,
6
+ "device": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "image_mean": [
13
+ 0.485,
14
+ 0.456,
15
+ 0.406
16
+ ],
17
+ "image_processor_type": "GotOcr2ImageProcessorFast",
18
+ "image_std": [
19
+ 0.229,
20
+ 0.224,
21
+ 0.225
22
+ ],
23
+ "input_data_format": null,
24
+ "max_patches": 12,
25
+ "min_patches": 1,
26
+ "processor_class": "InternVLProcessor",
27
+ "resample": 3,
28
+ "rescale_factor": 0.00392156862745098,
29
+ "return_tensors": null,
30
+ "size": {
31
+ "height": 448,
32
+ "width": 448
33
+ }
34
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "InternVLProcessor"
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,1051 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_start|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<repo_name>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<reponame>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<file_sep>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<filename>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<gh_stars>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<issue_start>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "<issue_comment>",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<issue_closed>",
75
+ "lstrip": false,
76
+ "normalized": false,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "<jupyter_start>",
82
+ "lstrip": false,
83
+ "normalized": false,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<jupyter_text>",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "<jupyter_code>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "<jupyter_output>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "<jupyter_script>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "<empty_output>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "<global-img>",
124
+ "lstrip": false,
125
+ "normalized": false,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "<row_1_col_1>",
131
+ "lstrip": false,
132
+ "normalized": false,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "<row_1_col_2>",
138
+ "lstrip": false,
139
+ "normalized": false,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "<row_1_col_3>",
145
+ "lstrip": false,
146
+ "normalized": false,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "<row_1_col_4>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ },
157
+ {
158
+ "content": "<row_1_col_5>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false
163
+ },
164
+ {
165
+ "content": "<row_1_col_6>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false
170
+ },
171
+ {
172
+ "content": "<row_2_col_1>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false
177
+ },
178
+ {
179
+ "content": "<row_2_col_2>",
180
+ "lstrip": false,
181
+ "normalized": false,
182
+ "rstrip": false,
183
+ "single_word": false
184
+ },
185
+ {
186
+ "content": "<row_2_col_3>",
187
+ "lstrip": false,
188
+ "normalized": false,
189
+ "rstrip": false,
190
+ "single_word": false
191
+ },
192
+ {
193
+ "content": "<row_2_col_4>",
194
+ "lstrip": false,
195
+ "normalized": false,
196
+ "rstrip": false,
197
+ "single_word": false
198
+ },
199
+ {
200
+ "content": "<row_2_col_5>",
201
+ "lstrip": false,
202
+ "normalized": false,
203
+ "rstrip": false,
204
+ "single_word": false
205
+ },
206
+ {
207
+ "content": "<row_2_col_6>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ {
214
+ "content": "<row_3_col_1>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ {
221
+ "content": "<row_3_col_2>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ {
228
+ "content": "<row_3_col_3>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ {
235
+ "content": "<row_3_col_4>",
236
+ "lstrip": false,
237
+ "normalized": false,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ {
242
+ "content": "<row_3_col_5>",
243
+ "lstrip": false,
244
+ "normalized": false,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ {
249
+ "content": "<row_3_col_6>",
250
+ "lstrip": false,
251
+ "normalized": false,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ },
255
+ {
256
+ "content": "<row_4_col_1>",
257
+ "lstrip": false,
258
+ "normalized": false,
259
+ "rstrip": false,
260
+ "single_word": false
261
+ },
262
+ {
263
+ "content": "<row_4_col_2>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false
268
+ },
269
+ {
270
+ "content": "<row_4_col_3>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false
275
+ },
276
+ {
277
+ "content": "<row_4_col_4>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false
282
+ },
283
+ {
284
+ "content": "<row_4_col_5>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false
289
+ },
290
+ {
291
+ "content": "<row_4_col_6>",
292
+ "lstrip": false,
293
+ "normalized": false,
294
+ "rstrip": false,
295
+ "single_word": false
296
+ },
297
+ {
298
+ "content": "<row_5_col_1>",
299
+ "lstrip": false,
300
+ "normalized": false,
301
+ "rstrip": false,
302
+ "single_word": false
303
+ },
304
+ {
305
+ "content": "<row_5_col_2>",
306
+ "lstrip": false,
307
+ "normalized": false,
308
+ "rstrip": false,
309
+ "single_word": false
310
+ },
311
+ {
312
+ "content": "<row_5_col_3>",
313
+ "lstrip": false,
314
+ "normalized": false,
315
+ "rstrip": false,
316
+ "single_word": false
317
+ },
318
+ {
319
+ "content": "<row_5_col_4>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false
324
+ },
325
+ {
326
+ "content": "<row_5_col_5>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false
331
+ },
332
+ {
333
+ "content": "<row_5_col_6>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false
338
+ },
339
+ {
340
+ "content": "<row_6_col_1>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false
345
+ },
346
+ {
347
+ "content": "<row_6_col_2>",
348
+ "lstrip": false,
349
+ "normalized": false,
350
+ "rstrip": false,
351
+ "single_word": false
352
+ },
353
+ {
354
+ "content": "<row_6_col_3>",
355
+ "lstrip": false,
356
+ "normalized": false,
357
+ "rstrip": false,
358
+ "single_word": false
359
+ },
360
+ {
361
+ "content": "<row_6_col_4>",
362
+ "lstrip": false,
363
+ "normalized": false,
364
+ "rstrip": false,
365
+ "single_word": false
366
+ },
367
+ {
368
+ "content": "<row_6_col_5>",
369
+ "lstrip": false,
370
+ "normalized": false,
371
+ "rstrip": false,
372
+ "single_word": false
373
+ },
374
+ {
375
+ "content": "<row_6_col_6>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false
380
+ },
381
+ {
382
+ "content": "<fake_token_around_image>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false
387
+ },
388
+ {
389
+ "content": "<image>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false
394
+ },
395
+ {
396
+ "content": "<caption>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false
401
+ },
402
+ {
403
+ "content": "</caption>",
404
+ "lstrip": false,
405
+ "normalized": false,
406
+ "rstrip": false,
407
+ "single_word": false
408
+ },
409
+ {
410
+ "content": "<footnote>",
411
+ "lstrip": false,
412
+ "normalized": false,
413
+ "rstrip": false,
414
+ "single_word": false
415
+ },
416
+ {
417
+ "content": "<|reserved_special_token_3|>",
418
+ "lstrip": false,
419
+ "normalized": false,
420
+ "rstrip": false,
421
+ "single_word": false
422
+ },
423
+ {
424
+ "content": "</footnote>",
425
+ "lstrip": false,
426
+ "normalized": false,
427
+ "rstrip": false,
428
+ "single_word": false
429
+ },
430
+ {
431
+ "content": "<formula>",
432
+ "lstrip": false,
433
+ "normalized": false,
434
+ "rstrip": false,
435
+ "single_word": false
436
+ },
437
+ {
438
+ "content": "</formula>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false
443
+ },
444
+ {
445
+ "content": "<list_item>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false
450
+ },
451
+ {
452
+ "content": "</list_item>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false
457
+ },
458
+ {
459
+ "content": "<page_footer>",
460
+ "lstrip": false,
461
+ "normalized": false,
462
+ "rstrip": false,
463
+ "single_word": false
464
+ },
465
+ {
466
+ "content": "</page_footer>",
467
+ "lstrip": false,
468
+ "normalized": false,
469
+ "rstrip": false,
470
+ "single_word": false
471
+ },
472
+ {
473
+ "content": "<page_header>",
474
+ "lstrip": false,
475
+ "normalized": false,
476
+ "rstrip": false,
477
+ "single_word": false
478
+ },
479
+ {
480
+ "content": "</page_header>",
481
+ "lstrip": false,
482
+ "normalized": false,
483
+ "rstrip": false,
484
+ "single_word": false
485
+ },
486
+ {
487
+ "content": "<picture>",
488
+ "lstrip": false,
489
+ "normalized": false,
490
+ "rstrip": false,
491
+ "single_word": false
492
+ },
493
+ {
494
+ "content": "</picture>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false
499
+ },
500
+ {
501
+ "content": "<section_header_level_",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false
506
+ },
507
+ {
508
+ "content": "</section_header_level_",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false
513
+ },
514
+ {
515
+ "content": "<otsl>",
516
+ "lstrip": false,
517
+ "normalized": false,
518
+ "rstrip": false,
519
+ "single_word": false
520
+ },
521
+ {
522
+ "content": "</otsl>",
523
+ "lstrip": false,
524
+ "normalized": false,
525
+ "rstrip": false,
526
+ "single_word": false
527
+ },
528
+ {
529
+ "content": "<checkbox_selected>",
530
+ "lstrip": false,
531
+ "normalized": false,
532
+ "rstrip": false,
533
+ "single_word": false
534
+ },
535
+ {
536
+ "content": "</checkbox_selected>",
537
+ "lstrip": false,
538
+ "normalized": false,
539
+ "rstrip": false,
540
+ "single_word": false
541
+ },
542
+ {
543
+ "content": "<checkbox_unselected>",
544
+ "lstrip": false,
545
+ "normalized": false,
546
+ "rstrip": false,
547
+ "single_word": false
548
+ },
549
+ {
550
+ "content": "</checkbox_unselected>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false
555
+ },
556
+ {
557
+ "content": "<form>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false
562
+ },
563
+ {
564
+ "content": "</form>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false
569
+ },
570
+ {
571
+ "content": "<key_value_region>",
572
+ "lstrip": false,
573
+ "normalized": false,
574
+ "rstrip": false,
575
+ "single_word": false
576
+ },
577
+ {
578
+ "content": "</key_value_region>",
579
+ "lstrip": false,
580
+ "normalized": false,
581
+ "rstrip": false,
582
+ "single_word": false
583
+ },
584
+ {
585
+ "content": "<loc_",
586
+ "lstrip": false,
587
+ "normalized": false,
588
+ "rstrip": false,
589
+ "single_word": false
590
+ },
591
+ {
592
+ "content": "<paragraph>",
593
+ "lstrip": false,
594
+ "normalized": false,
595
+ "rstrip": false,
596
+ "single_word": false
597
+ },
598
+ {
599
+ "content": "</paragraph>",
600
+ "lstrip": false,
601
+ "normalized": false,
602
+ "rstrip": false,
603
+ "single_word": false
604
+ },
605
+ {
606
+ "content": "<reference>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false
611
+ },
612
+ {
613
+ "content": "</reference>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false
618
+ },
619
+ {
620
+ "content": "<ordered_list>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false
625
+ },
626
+ {
627
+ "content": "</ordered_list>",
628
+ "lstrip": false,
629
+ "normalized": false,
630
+ "rstrip": false,
631
+ "single_word": false
632
+ },
633
+ {
634
+ "content": "<unordered_list>",
635
+ "lstrip": false,
636
+ "normalized": false,
637
+ "rstrip": false,
638
+ "single_word": false
639
+ },
640
+ {
641
+ "content": "</unordered_list>",
642
+ "lstrip": false,
643
+ "normalized": false,
644
+ "rstrip": false,
645
+ "single_word": false
646
+ },
647
+ {
648
+ "content": "<group>",
649
+ "lstrip": false,
650
+ "normalized": false,
651
+ "rstrip": false,
652
+ "single_word": false
653
+ },
654
+ {
655
+ "content": "</group>",
656
+ "lstrip": false,
657
+ "normalized": false,
658
+ "rstrip": false,
659
+ "single_word": false
660
+ },
661
+ {
662
+ "content": "<doctag>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false
667
+ },
668
+ {
669
+ "content": "</doctag>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false
674
+ },
675
+ {
676
+ "content": "<page_",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false
681
+ },
682
+ {
683
+ "content": "<text_break>",
684
+ "lstrip": false,
685
+ "normalized": false,
686
+ "rstrip": false,
687
+ "single_word": false
688
+ },
689
+ {
690
+ "content": "<fcel>",
691
+ "lstrip": false,
692
+ "normalized": false,
693
+ "rstrip": false,
694
+ "single_word": false
695
+ },
696
+ {
697
+ "content": "<ecel>",
698
+ "lstrip": false,
699
+ "normalized": false,
700
+ "rstrip": false,
701
+ "single_word": false
702
+ },
703
+ {
704
+ "content": "<lcel>",
705
+ "lstrip": false,
706
+ "normalized": false,
707
+ "rstrip": false,
708
+ "single_word": false
709
+ },
710
+ {
711
+ "content": "<ucel>",
712
+ "lstrip": false,
713
+ "normalized": false,
714
+ "rstrip": false,
715
+ "single_word": false
716
+ },
717
+ {
718
+ "content": "<xcel>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false
723
+ },
724
+ {
725
+ "content": "<nl>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false
730
+ },
731
+ {
732
+ "content": "<ched>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false
737
+ },
738
+ {
739
+ "content": "<rhed>",
740
+ "lstrip": false,
741
+ "normalized": false,
742
+ "rstrip": false,
743
+ "single_word": false
744
+ },
745
+ {
746
+ "content": "<|reserved_special_token_50|>",
747
+ "lstrip": false,
748
+ "normalized": false,
749
+ "rstrip": false,
750
+ "single_word": false
751
+ },
752
+ {
753
+ "content": "<key_",
754
+ "lstrip": false,
755
+ "normalized": false,
756
+ "rstrip": false,
757
+ "single_word": false
758
+ },
759
+ {
760
+ "content": "</key_",
761
+ "lstrip": false,
762
+ "normalized": false,
763
+ "rstrip": false,
764
+ "single_word": false
765
+ },
766
+ {
767
+ "content": "<value_",
768
+ "lstrip": false,
769
+ "normalized": false,
770
+ "rstrip": false,
771
+ "single_word": false
772
+ },
773
+ {
774
+ "content": "</value_",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false
779
+ },
780
+ {
781
+ "content": "<link_",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false
786
+ },
787
+ {
788
+ "content": "<chart>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false
793
+ },
794
+ {
795
+ "content": "</chart>",
796
+ "lstrip": false,
797
+ "normalized": false,
798
+ "rstrip": false,
799
+ "single_word": false
800
+ },
801
+ {
802
+ "content": "<page_break>",
803
+ "lstrip": false,
804
+ "normalized": false,
805
+ "rstrip": false,
806
+ "single_word": false
807
+ },
808
+ {
809
+ "content": "<smiles>",
810
+ "lstrip": false,
811
+ "normalized": false,
812
+ "rstrip": false,
813
+ "single_word": false
814
+ },
815
+ {
816
+ "content": "</smiles>",
817
+ "lstrip": false,
818
+ "normalized": false,
819
+ "rstrip": false,
820
+ "single_word": false
821
+ },
822
+ {
823
+ "content": "<|reserved_special_token_61|>",
824
+ "lstrip": false,
825
+ "normalized": false,
826
+ "rstrip": false,
827
+ "single_word": false
828
+ },
829
+ {
830
+ "content": "<|reserved_special_token_62|>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false
835
+ },
836
+ {
837
+ "content": "<|reserved_special_token_63|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false
842
+ },
843
+ {
844
+ "content": "<|reserved_special_token_64|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false
849
+ },
850
+ {
851
+ "content": "<|reserved_special_token_65|>",
852
+ "lstrip": false,
853
+ "normalized": false,
854
+ "rstrip": false,
855
+ "single_word": false
856
+ },
857
+ {
858
+ "content": "<|reserved_special_token_66|>",
859
+ "lstrip": false,
860
+ "normalized": false,
861
+ "rstrip": false,
862
+ "single_word": false
863
+ },
864
+ {
865
+ "content": "<|reserved_special_token_67|>",
866
+ "lstrip": false,
867
+ "normalized": false,
868
+ "rstrip": false,
869
+ "single_word": false
870
+ },
871
+ {
872
+ "content": "<|reserved_special_token_68|>",
873
+ "lstrip": false,
874
+ "normalized": false,
875
+ "rstrip": false,
876
+ "single_word": false
877
+ },
878
+ {
879
+ "content": "<|reserved_special_token_69|>",
880
+ "lstrip": false,
881
+ "normalized": false,
882
+ "rstrip": false,
883
+ "single_word": false
884
+ },
885
+ {
886
+ "content": "<|reserved_special_token_70|>",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false
891
+ },
892
+ {
893
+ "content": "<|reserved_special_token_71|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false
898
+ },
899
+ {
900
+ "content": "<|reserved_special_token_72|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false
905
+ },
906
+ {
907
+ "content": "<|reserved_special_token_73|>",
908
+ "lstrip": false,
909
+ "normalized": false,
910
+ "rstrip": false,
911
+ "single_word": false
912
+ },
913
+ {
914
+ "content": "<|reserved_special_token_74|>",
915
+ "lstrip": false,
916
+ "normalized": false,
917
+ "rstrip": false,
918
+ "single_word": false
919
+ },
920
+ {
921
+ "content": "<|reserved_special_token_75|>",
922
+ "lstrip": false,
923
+ "normalized": false,
924
+ "rstrip": false,
925
+ "single_word": false
926
+ },
927
+ {
928
+ "content": "<|reserved_special_token_76|>",
929
+ "lstrip": false,
930
+ "normalized": false,
931
+ "rstrip": false,
932
+ "single_word": false
933
+ },
934
+ {
935
+ "content": "<|reserved_special_token_77|>",
936
+ "lstrip": false,
937
+ "normalized": false,
938
+ "rstrip": false,
939
+ "single_word": false
940
+ },
941
+ {
942
+ "content": "<|reserved_special_token_78|>",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false
947
+ },
948
+ {
949
+ "content": "<|reserved_special_token_79|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false
954
+ },
955
+ {
956
+ "content": "<|reserved_special_token_80|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false
961
+ },
962
+ {
963
+ "content": "<|reserved_special_token_81|>",
964
+ "lstrip": false,
965
+ "normalized": false,
966
+ "rstrip": false,
967
+ "single_word": false
968
+ },
969
+ {
970
+ "content": "<|reserved_special_token_82|>",
971
+ "lstrip": false,
972
+ "normalized": false,
973
+ "rstrip": false,
974
+ "single_word": false
975
+ },
976
+ {
977
+ "content": "<|reserved_special_token_83|>",
978
+ "lstrip": false,
979
+ "normalized": false,
980
+ "rstrip": false,
981
+ "single_word": false
982
+ },
983
+ {
984
+ "content": "<|reserved_special_token_84|>",
985
+ "lstrip": false,
986
+ "normalized": false,
987
+ "rstrip": false,
988
+ "single_word": false
989
+ },
990
+ {
991
+ "content": "<|reserved_special_token_85|>",
992
+ "lstrip": false,
993
+ "normalized": false,
994
+ "rstrip": false,
995
+ "single_word": false
996
+ },
997
+ {
998
+ "content": "<|reserved_special_token_86|>",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false
1003
+ },
1004
+ {
1005
+ "content": "<|reserved_special_token_87|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false
1010
+ },
1011
+ {
1012
+ "content": "<end_of_utterance>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false
1017
+ },
1018
+ {
1019
+ "content": "<|value|>",
1020
+ "lstrip": false,
1021
+ "normalized": false,
1022
+ "rstrip": false,
1023
+ "single_word": false
1024
+ },
1025
+ {
1026
+ "content": "<|bbox|>",
1027
+ "lstrip": false,
1028
+ "normalized": false,
1029
+ "rstrip": false,
1030
+ "single_word": false
1031
+ }
1032
+ ],
1033
+ "context_image_token": "<IMG_CONTEXT>",
1034
+ "end_image_token": "</img>",
1035
+ "eos_token": {
1036
+ "content": "<|im_end|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false
1041
+ },
1042
+ "pad_token": {
1043
+ "content": "<|endoftext|>",
1044
+ "lstrip": false,
1045
+ "normalized": false,
1046
+ "rstrip": false,
1047
+ "single_word": false
1048
+ },
1049
+ "start_image_token": "<img>",
1050
+ "video_token": "<video>"
1051
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68bc3eac926eca434899018b975b672b12b88037f6234c93be84eefa9e310c53
3
+ size 11451419
tokenizer_config.json ADDED
@@ -0,0 +1,1584 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "151674": {
254
+ "content": "<video>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "<repo_name>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "151676": {
270
+ "content": "<reponame>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "151677": {
278
+ "content": "<file_sep>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "151678": {
286
+ "content": "<filename>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "151679": {
294
+ "content": "<gh_stars>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "151680": {
302
+ "content": "<issue_start>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "151681": {
310
+ "content": "<issue_comment>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "151682": {
318
+ "content": "<issue_closed>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "151683": {
326
+ "content": "<jupyter_start>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "151684": {
334
+ "content": "<jupyter_text>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "151685": {
342
+ "content": "<jupyter_code>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "151686": {
350
+ "content": "<jupyter_output>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "151687": {
358
+ "content": "<jupyter_script>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "151688": {
366
+ "content": "<empty_output>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "151689": {
374
+ "content": "<global-img>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "151690": {
382
+ "content": "<row_1_col_1>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "151691": {
390
+ "content": "<row_1_col_2>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "151692": {
398
+ "content": "<row_1_col_3>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "151693": {
406
+ "content": "<row_1_col_4>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "151694": {
414
+ "content": "<row_1_col_5>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "151695": {
422
+ "content": "<row_1_col_6>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "151696": {
430
+ "content": "<row_2_col_1>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "151697": {
438
+ "content": "<row_2_col_2>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "151698": {
446
+ "content": "<row_2_col_3>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "151699": {
454
+ "content": "<row_2_col_4>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "151700": {
462
+ "content": "<row_2_col_5>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "151701": {
470
+ "content": "<row_2_col_6>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "151702": {
478
+ "content": "<row_3_col_1>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "151703": {
486
+ "content": "<row_3_col_2>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "151704": {
494
+ "content": "<row_3_col_3>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "151705": {
502
+ "content": "<row_3_col_4>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "151706": {
510
+ "content": "<row_3_col_5>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "151707": {
518
+ "content": "<row_3_col_6>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "151708": {
526
+ "content": "<row_4_col_1>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "151709": {
534
+ "content": "<row_4_col_2>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "151710": {
542
+ "content": "<row_4_col_3>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "151711": {
550
+ "content": "<row_4_col_4>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "151712": {
558
+ "content": "<row_4_col_5>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "151713": {
566
+ "content": "<row_4_col_6>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "151714": {
574
+ "content": "<row_5_col_1>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "151715": {
582
+ "content": "<row_5_col_2>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "151716": {
590
+ "content": "<row_5_col_3>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "151717": {
598
+ "content": "<row_5_col_4>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "151718": {
606
+ "content": "<row_5_col_5>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "151719": {
614
+ "content": "<row_5_col_6>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "151720": {
622
+ "content": "<row_6_col_1>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "151721": {
630
+ "content": "<row_6_col_2>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "151722": {
638
+ "content": "<row_6_col_3>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "151723": {
646
+ "content": "<row_6_col_4>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "151724": {
654
+ "content": "<row_6_col_5>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "151725": {
662
+ "content": "<row_6_col_6>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "151726": {
670
+ "content": "<fake_token_around_image>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "151727": {
678
+ "content": "<image>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "151728": {
686
+ "content": "<caption>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "151729": {
694
+ "content": "</caption>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "151730": {
702
+ "content": "<footnote>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "151731": {
710
+ "content": "<|reserved_special_token_3|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "151732": {
718
+ "content": "</footnote>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "151733": {
726
+ "content": "<formula>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "151734": {
734
+ "content": "</formula>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "151735": {
742
+ "content": "<list_item>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "151736": {
750
+ "content": "</list_item>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "151737": {
758
+ "content": "<page_footer>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "151738": {
766
+ "content": "</page_footer>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ },
773
+ "151739": {
774
+ "content": "<page_header>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": true
780
+ },
781
+ "151740": {
782
+ "content": "</page_header>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": true
788
+ },
789
+ "151741": {
790
+ "content": "<picture>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": true
796
+ },
797
+ "151742": {
798
+ "content": "</picture>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": true
804
+ },
805
+ "151743": {
806
+ "content": "<section_header_level_",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": true
812
+ },
813
+ "151744": {
814
+ "content": "</section_header_level_",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": true
820
+ },
821
+ "151745": {
822
+ "content": "<otsl>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": true
828
+ },
829
+ "151746": {
830
+ "content": "</otsl>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": true
836
+ },
837
+ "151747": {
838
+ "content": "<checkbox_selected>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": true
844
+ },
845
+ "151748": {
846
+ "content": "</checkbox_selected>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": true
852
+ },
853
+ "151749": {
854
+ "content": "<checkbox_unselected>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "151750": {
862
+ "content": "</checkbox_unselected>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "151751": {
870
+ "content": "<form>",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": true
876
+ },
877
+ "151752": {
878
+ "content": "</form>",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": true
884
+ },
885
+ "151753": {
886
+ "content": "<key_value_region>",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": true
892
+ },
893
+ "151754": {
894
+ "content": "</key_value_region>",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": true
900
+ },
901
+ "151755": {
902
+ "content": "<loc_",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": true
908
+ },
909
+ "151756": {
910
+ "content": "<paragraph>",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": true
916
+ },
917
+ "151757": {
918
+ "content": "</paragraph>",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": true
924
+ },
925
+ "151758": {
926
+ "content": "<reference>",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": true
932
+ },
933
+ "151759": {
934
+ "content": "</reference>",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": true
940
+ },
941
+ "151760": {
942
+ "content": "<ordered_list>",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": true
948
+ },
949
+ "151761": {
950
+ "content": "</ordered_list>",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": true
956
+ },
957
+ "151762": {
958
+ "content": "<unordered_list>",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": true
964
+ },
965
+ "151763": {
966
+ "content": "</unordered_list>",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": true
972
+ },
973
+ "151764": {
974
+ "content": "<group>",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": true
980
+ },
981
+ "151765": {
982
+ "content": "</group>",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": true
988
+ },
989
+ "151766": {
990
+ "content": "<doctag>",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": true
996
+ },
997
+ "151767": {
998
+ "content": "</doctag>",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": true
1004
+ },
1005
+ "151768": {
1006
+ "content": "<page_",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": true
1012
+ },
1013
+ "151769": {
1014
+ "content": "<text_break>",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": true
1020
+ },
1021
+ "151770": {
1022
+ "content": "<fcel>",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": true
1028
+ },
1029
+ "151771": {
1030
+ "content": "<ecel>",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": true
1036
+ },
1037
+ "151772": {
1038
+ "content": "<lcel>",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": true
1044
+ },
1045
+ "151773": {
1046
+ "content": "<ucel>",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": true
1052
+ },
1053
+ "151774": {
1054
+ "content": "<xcel>",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": true
1060
+ },
1061
+ "151775": {
1062
+ "content": "<nl>",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": true
1068
+ },
1069
+ "151776": {
1070
+ "content": "<ched>",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": true
1076
+ },
1077
+ "151777": {
1078
+ "content": "<rhed>",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": true
1084
+ },
1085
+ "151778": {
1086
+ "content": "<|reserved_special_token_50|>",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": true
1092
+ },
1093
+ "151779": {
1094
+ "content": "<key_",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": true
1100
+ },
1101
+ "151780": {
1102
+ "content": "</key_",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": true
1108
+ },
1109
+ "151781": {
1110
+ "content": "<value_",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": true
1116
+ },
1117
+ "151782": {
1118
+ "content": "</value_",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": true
1124
+ },
1125
+ "151783": {
1126
+ "content": "<link_",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": true
1132
+ },
1133
+ "151784": {
1134
+ "content": "<chart>",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": true
1140
+ },
1141
+ "151785": {
1142
+ "content": "</chart>",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": true
1148
+ },
1149
+ "151786": {
1150
+ "content": "<page_break>",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": true
1156
+ },
1157
+ "151787": {
1158
+ "content": "<smiles>",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": true
1164
+ },
1165
+ "151788": {
1166
+ "content": "</smiles>",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": true
1172
+ },
1173
+ "151789": {
1174
+ "content": "<|reserved_special_token_61|>",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": true
1180
+ },
1181
+ "151790": {
1182
+ "content": "<|reserved_special_token_62|>",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": true
1188
+ },
1189
+ "151791": {
1190
+ "content": "<|reserved_special_token_63|>",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": true
1196
+ },
1197
+ "151792": {
1198
+ "content": "<|reserved_special_token_64|>",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": true
1204
+ },
1205
+ "151793": {
1206
+ "content": "<|reserved_special_token_65|>",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": true
1212
+ },
1213
+ "151794": {
1214
+ "content": "<|reserved_special_token_66|>",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": true
1220
+ },
1221
+ "151795": {
1222
+ "content": "<|reserved_special_token_67|>",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": true
1228
+ },
1229
+ "151796": {
1230
+ "content": "<|reserved_special_token_68|>",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": true
1236
+ },
1237
+ "151797": {
1238
+ "content": "<|reserved_special_token_69|>",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": true
1244
+ },
1245
+ "151798": {
1246
+ "content": "<|reserved_special_token_70|>",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": true
1252
+ },
1253
+ "151799": {
1254
+ "content": "<|reserved_special_token_71|>",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": true
1260
+ },
1261
+ "151800": {
1262
+ "content": "<|reserved_special_token_72|>",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": true
1268
+ },
1269
+ "151801": {
1270
+ "content": "<|reserved_special_token_73|>",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": true
1276
+ },
1277
+ "151802": {
1278
+ "content": "<|reserved_special_token_74|>",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": true
1284
+ },
1285
+ "151803": {
1286
+ "content": "<|reserved_special_token_75|>",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": true
1292
+ },
1293
+ "151804": {
1294
+ "content": "<|reserved_special_token_76|>",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": true
1300
+ },
1301
+ "151805": {
1302
+ "content": "<|reserved_special_token_77|>",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": true
1308
+ },
1309
+ "151806": {
1310
+ "content": "<|reserved_special_token_78|>",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": true
1316
+ },
1317
+ "151807": {
1318
+ "content": "<|reserved_special_token_79|>",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": true
1324
+ },
1325
+ "151808": {
1326
+ "content": "<|reserved_special_token_80|>",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": true
1332
+ },
1333
+ "151809": {
1334
+ "content": "<|reserved_special_token_81|>",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": true
1340
+ },
1341
+ "151810": {
1342
+ "content": "<|reserved_special_token_82|>",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": true
1348
+ },
1349
+ "151811": {
1350
+ "content": "<|reserved_special_token_83|>",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": true
1356
+ },
1357
+ "151812": {
1358
+ "content": "<|reserved_special_token_84|>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": true
1364
+ },
1365
+ "151813": {
1366
+ "content": "<|reserved_special_token_85|>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": true
1372
+ },
1373
+ "151814": {
1374
+ "content": "<|reserved_special_token_86|>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": true
1380
+ },
1381
+ "151815": {
1382
+ "content": "<|reserved_special_token_87|>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": true
1388
+ },
1389
+ "151816": {
1390
+ "content": "<end_of_utterance>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": true
1396
+ },
1397
+ "151817": {
1398
+ "content": "<|value|>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": true
1404
+ },
1405
+ "151818": {
1406
+ "content": "<|bbox|>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": true
1412
+ }
1413
+ },
1414
+ "additional_special_tokens": [
1415
+ "<|endoftext|>",
1416
+ "<|im_start|>",
1417
+ "<|im_end|>",
1418
+ "<repo_name>",
1419
+ "<reponame>",
1420
+ "<file_sep>",
1421
+ "<filename>",
1422
+ "<gh_stars>",
1423
+ "<issue_start>",
1424
+ "<issue_comment>",
1425
+ "<issue_closed>",
1426
+ "<jupyter_start>",
1427
+ "<jupyter_text>",
1428
+ "<jupyter_code>",
1429
+ "<jupyter_output>",
1430
+ "<jupyter_script>",
1431
+ "<empty_output>",
1432
+ "<global-img>",
1433
+ "<row_1_col_1>",
1434
+ "<row_1_col_2>",
1435
+ "<row_1_col_3>",
1436
+ "<row_1_col_4>",
1437
+ "<row_1_col_5>",
1438
+ "<row_1_col_6>",
1439
+ "<row_2_col_1>",
1440
+ "<row_2_col_2>",
1441
+ "<row_2_col_3>",
1442
+ "<row_2_col_4>",
1443
+ "<row_2_col_5>",
1444
+ "<row_2_col_6>",
1445
+ "<row_3_col_1>",
1446
+ "<row_3_col_2>",
1447
+ "<row_3_col_3>",
1448
+ "<row_3_col_4>",
1449
+ "<row_3_col_5>",
1450
+ "<row_3_col_6>",
1451
+ "<row_4_col_1>",
1452
+ "<row_4_col_2>",
1453
+ "<row_4_col_3>",
1454
+ "<row_4_col_4>",
1455
+ "<row_4_col_5>",
1456
+ "<row_4_col_6>",
1457
+ "<row_5_col_1>",
1458
+ "<row_5_col_2>",
1459
+ "<row_5_col_3>",
1460
+ "<row_5_col_4>",
1461
+ "<row_5_col_5>",
1462
+ "<row_5_col_6>",
1463
+ "<row_6_col_1>",
1464
+ "<row_6_col_2>",
1465
+ "<row_6_col_3>",
1466
+ "<row_6_col_4>",
1467
+ "<row_6_col_5>",
1468
+ "<row_6_col_6>",
1469
+ "<fake_token_around_image>",
1470
+ "<image>",
1471
+ "<caption>",
1472
+ "</caption>",
1473
+ "<footnote>",
1474
+ "<|reserved_special_token_3|>",
1475
+ "</footnote>",
1476
+ "<formula>",
1477
+ "</formula>",
1478
+ "<list_item>",
1479
+ "</list_item>",
1480
+ "<page_footer>",
1481
+ "</page_footer>",
1482
+ "<page_header>",
1483
+ "</page_header>",
1484
+ "<picture>",
1485
+ "</picture>",
1486
+ "<section_header_level_",
1487
+ "</section_header_level_",
1488
+ "<otsl>",
1489
+ "</otsl>",
1490
+ "<checkbox_selected>",
1491
+ "</checkbox_selected>",
1492
+ "<checkbox_unselected>",
1493
+ "</checkbox_unselected>",
1494
+ "<form>",
1495
+ "</form>",
1496
+ "<key_value_region>",
1497
+ "</key_value_region>",
1498
+ "<loc_",
1499
+ "<paragraph>",
1500
+ "</paragraph>",
1501
+ "<reference>",
1502
+ "</reference>",
1503
+ "<ordered_list>",
1504
+ "</ordered_list>",
1505
+ "<unordered_list>",
1506
+ "</unordered_list>",
1507
+ "<group>",
1508
+ "</group>",
1509
+ "<doctag>",
1510
+ "</doctag>",
1511
+ "<page_",
1512
+ "<text_break>",
1513
+ "<fcel>",
1514
+ "<ecel>",
1515
+ "<lcel>",
1516
+ "<ucel>",
1517
+ "<xcel>",
1518
+ "<nl>",
1519
+ "<ched>",
1520
+ "<rhed>",
1521
+ "<|reserved_special_token_50|>",
1522
+ "<key_",
1523
+ "</key_",
1524
+ "<value_",
1525
+ "</value_",
1526
+ "<link_",
1527
+ "<chart>",
1528
+ "</chart>",
1529
+ "<page_break>",
1530
+ "<smiles>",
1531
+ "</smiles>",
1532
+ "<|reserved_special_token_61|>",
1533
+ "<|reserved_special_token_62|>",
1534
+ "<|reserved_special_token_63|>",
1535
+ "<|reserved_special_token_64|>",
1536
+ "<|reserved_special_token_65|>",
1537
+ "<|reserved_special_token_66|>",
1538
+ "<|reserved_special_token_67|>",
1539
+ "<|reserved_special_token_68|>",
1540
+ "<|reserved_special_token_69|>",
1541
+ "<|reserved_special_token_70|>",
1542
+ "<|reserved_special_token_71|>",
1543
+ "<|reserved_special_token_72|>",
1544
+ "<|reserved_special_token_73|>",
1545
+ "<|reserved_special_token_74|>",
1546
+ "<|reserved_special_token_75|>",
1547
+ "<|reserved_special_token_76|>",
1548
+ "<|reserved_special_token_77|>",
1549
+ "<|reserved_special_token_78|>",
1550
+ "<|reserved_special_token_79|>",
1551
+ "<|reserved_special_token_80|>",
1552
+ "<|reserved_special_token_81|>",
1553
+ "<|reserved_special_token_82|>",
1554
+ "<|reserved_special_token_83|>",
1555
+ "<|reserved_special_token_84|>",
1556
+ "<|reserved_special_token_85|>",
1557
+ "<|reserved_special_token_86|>",
1558
+ "<|reserved_special_token_87|>",
1559
+ "<end_of_utterance>",
1560
+ "<|value|>",
1561
+ "<|bbox|>"
1562
+ ],
1563
+ "bos_token": null,
1564
+ "clean_up_tokenization_spaces": false,
1565
+ "context_image_token": "<IMG_CONTEXT>",
1566
+ "end_image_token": "</img>",
1567
+ "eos_token": "<|im_end|>",
1568
+ "errors": "replace",
1569
+ "extra_special_tokens": {
1570
+ "context_image_token": "<IMG_CONTEXT>",
1571
+ "end_image_token": "</img>",
1572
+ "start_image_token": "<img>",
1573
+ "video_token": "<video>"
1574
+ },
1575
+ "model_max_length": 8192,
1576
+ "pad_token": "<|endoftext|>",
1577
+ "processor_class": "InternVLProcessor",
1578
+ "return_token_type_ids": false,
1579
+ "split_special_tokens": false,
1580
+ "start_image_token": "<img>",
1581
+ "tokenizer_class": "Qwen2Tokenizer",
1582
+ "unk_token": null,
1583
+ "video_token": "<video>"
1584
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_kwargs_names": [
3
+ "do_convert_rgb",
4
+ "do_resize",
5
+ "size",
6
+ "size_divisor",
7
+ "default_to_square",
8
+ "resample",
9
+ "do_rescale",
10
+ "rescale_factor",
11
+ "do_normalize",
12
+ "image_mean",
13
+ "image_std",
14
+ "do_pad",
15
+ "do_center_crop",
16
+ "crop_size",
17
+ "data_format",
18
+ "input_data_format",
19
+ "device"
20
+ ],
21
+ "crop_size": null,
22
+ "crop_to_patches": false,
23
+ "data_format": "channels_first",
24
+ "default_to_square": true,
25
+ "device": null,
26
+ "do_center_crop": null,
27
+ "do_convert_rgb": true,
28
+ "do_normalize": true,
29
+ "do_pad": null,
30
+ "do_rescale": true,
31
+ "do_resize": true,
32
+ "image_mean": [
33
+ 0.485,
34
+ 0.456,
35
+ 0.406
36
+ ],
37
+ "image_processor_type": "GotOcr2ImageProcessorFast",
38
+ "image_std": [
39
+ 0.229,
40
+ 0.224,
41
+ 0.225
42
+ ],
43
+ "input_data_format": null,
44
+ "max_patches": 12,
45
+ "min_patches": 1,
46
+ "model_valid_processing_keys": [
47
+ "do_convert_rgb",
48
+ "do_resize",
49
+ "size",
50
+ "size_divisor",
51
+ "default_to_square",
52
+ "resample",
53
+ "do_rescale",
54
+ "rescale_factor",
55
+ "do_normalize",
56
+ "image_mean",
57
+ "image_std",
58
+ "do_pad",
59
+ "do_center_crop",
60
+ "crop_size",
61
+ "data_format",
62
+ "input_data_format",
63
+ "device"
64
+ ],
65
+ "processor_class": "InternVLProcessor",
66
+ "resample": 3,
67
+ "rescale_factor": 0.00392156862745098,
68
+ "return_tensors": null,
69
+ "size": {
70
+ "height": 448,
71
+ "width": 448
72
+ },
73
+ "size_divisor": null,
74
+ "video_processor_type": "InternVLVideoProcessor"
75
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff