Hugging Face's logo

NCSOFT
/
VARCO-VISION-2.0-1.7B-OCR

Image-Text-to-Text
Transformers
Safetensors
English
Korean
llava_onevision
image-to-text
multimodal
OCR
ncsoft
ncai
varco
conversational
Model card Files
xet
Community
1
kimyoungjune commited on
Commit
350cb82
·
verified ·
1 Parent(s): 8c6c8c8

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +40 -0
  3. chat_template.jinja +10 -0
  4. config.json +237 -0
  5. generation_config.json +6 -0
  6. merges.txt +0 -0
  7. model.safetensors +3 -0
  8. preprocessor_config.json +171 -0
  9. processor_config.json +8 -0
  10. special_tokens_map.json +34 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +333 -0
  13. video_preprocessor_config.json +37 -0
  14. vocab.json +0 -0
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* 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
  examples.gif 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
  examples.gif filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</bbox>": 151677,
3
+ "</char>": 151673,
4
+ "</obj>": 151675,
5
+ "</think>": 151668,
6
+ "</tool_call>": 151658,
7
+ "</tool_response>": 151666,
8
+ "<bbox>": 151676,
9
+ "<char>": 151672,
10
+ "<delim>": 151678,
11
+ "<gro>": 151670,
12
+ "<image>": 151679,
13
+ "<obj>": 151674,
14
+ "<ocr>": 151671,
15
+ "<think>": 151667,
16
+ "<tool_call>": 151657,
17
+ "<tool_response>": 151665,
18
+ "<video>": 151680,
19
+ "<|box_end|>": 151649,
20
+ "<|box_start|>": 151648,
21
+ "<|endoftext|>": 151643,
22
+ "<|file_sep|>": 151664,
23
+ "<|fim_middle|>": 151660,
24
+ "<|fim_pad|>": 151662,
25
+ "<|fim_prefix|>": 151659,
26
+ "<|fim_suffix|>": 151661,
27
+ "<|im_end|>": 151645,
28
+ "<|im_start|>": 151644,
29
+ "<|image_pad|>": 151655,
30
+ "<|object_ref_end|>": 151647,
31
+ "<|object_ref_start|>": 151646,
32
+ "<|quad_end|>": 151651,
33
+ "<|quad_start|>": 151650,
34
+ "<|repo_name|>": 151663,
35
+ "<|video_pad|>": 151656,
36
+ "<|vision_end|>": 151653,
37
+ "<|vision_pad|>": 151654,
38
+ "<|vision_start|>": 151652,
39
+ "[UNK]": 151669
40
+ }
chat_template.jinja ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {% if messages[0]['role'] == 'system' %}{{'<|im_start|>system
2
+ ' + messages[0]['content'] + '<|im_end|>
3
+ '}}{% else %}{{'<|im_start|>system
4
+ You are VARCO-VISION, created by NC AI. You are a helpful assistant.<|im_end|>
5
+ '}}{% endif %}{% for message in messages %}{% if message['role'] == 'user' or message['role'] == 'system' and not loop.first or message['role'] == 'assistant' %}{{'<|im_start|>' + message['role'] + '
6
+ '}}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>
7
+ ' }}{% endfor %}{# Render all video then #}{% for content in message['content'] | selectattr('type', 'equalto', 'video') %}{{ '<video>
8
+ ' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] }}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] }}{% endgeneration %}{% endfor %}{% endif %}{{'<|im_end|>' + '
9
+ '}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
10
+ ' }}{% endif %}
config.json ADDED
@@ -0,0 +1,237 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaOnevisionForConditionalGeneration"
4
+ ],
5
+ "image_grid_pinpoints": [
6
+ [
7
+ 384,
8
+ 384
9
+ ],
10
+ [
11
+ 384,
12
+ 768
13
+ ],
14
+ [
15
+ 384,
16
+ 1152
17
+ ],
18
+ [
19
+ 384,
20
+ 1536
21
+ ],
22
+ [
23
+ 384,
24
+ 1920
25
+ ],
26
+ [
27
+ 384,
28
+ 2304
29
+ ],
30
+ [
31
+ 768,
32
+ 384
33
+ ],
34
+ [
35
+ 768,
36
+ 768
37
+ ],
38
+ [
39
+ 768,
40
+ 1152
41
+ ],
42
+ [
43
+ 768,
44
+ 1536
45
+ ],
46
+ [
47
+ 768,
48
+ 1920
49
+ ],
50
+ [
51
+ 768,
52
+ 2304
53
+ ],
54
+ [
55
+ 1152,
56
+ 384
57
+ ],
58
+ [
59
+ 1152,
60
+ 768
61
+ ],
62
+ [
63
+ 1152,
64
+ 1152
65
+ ],
66
+ [
67
+ 1152,
68
+ 1536
69
+ ],
70
+ [
71
+ 1152,
72
+ 1920
73
+ ],
74
+ [
75
+ 1152,
76
+ 2304
77
+ ],
78
+ [
79
+ 1536,
80
+ 384
81
+ ],
82
+ [
83
+ 1536,
84
+ 768
85
+ ],
86
+ [
87
+ 1536,
88
+ 1152
89
+ ],
90
+ [
91
+ 1536,
92
+ 1536
93
+ ],
94
+ [
95
+ 1536,
96
+ 1920
97
+ ],
98
+ [
99
+ 1536,
100
+ 2304
101
+ ],
102
+ [
103
+ 1920,
104
+ 384
105
+ ],
106
+ [
107
+ 1920,
108
+ 768
109
+ ],
110
+ [
111
+ 1920,
112
+ 1152
113
+ ],
114
+ [
115
+ 1920,
116
+ 1536
117
+ ],
118
+ [
119
+ 1920,
120
+ 1920
121
+ ],
122
+ [
123
+ 1920,
124
+ 2304
125
+ ],
126
+ [
127
+ 2304,
128
+ 384
129
+ ],
130
+ [
131
+ 2304,
132
+ 768
133
+ ],
134
+ [
135
+ 2304,
136
+ 1152
137
+ ],
138
+ [
139
+ 2304,
140
+ 1536
141
+ ],
142
+ [
143
+ 2304,
144
+ 1920
145
+ ],
146
+ [
147
+ 2304,
148
+ 2304
149
+ ]
150
+ ],
151
+ "image_token_index": 151679,
152
+ "model_type": "llava_onevision",
153
+ "multimodal_projector_bias": true,
154
+ "projector_hidden_act": "gelu",
155
+ "text_config": {
156
+ "_name_or_path": "Qwen/Qwen3-1.7B",
157
+ "architectures": [
158
+ "Qwen3ForCausalLM"
159
+ ],
160
+ "attention_bias": false,
161
+ "attention_dropout": 0.0,
162
+ "bos_token_id": 151643,
163
+ "eos_token_id": 151645,
164
+ "head_dim": 128,
165
+ "hidden_act": "silu",
166
+ "hidden_size": 2048,
167
+ "initializer_range": 0.02,
168
+ "intermediate_size": 6144,
169
+ "layer_types": [
170
+ "full_attention",
171
+ "full_attention",
172
+ "full_attention",
173
+ "full_attention",
174
+ "full_attention",
175
+ "full_attention",
176
+ "full_attention",
177
+ "full_attention",
178
+ "full_attention",
179
+ "full_attention",
180
+ "full_attention",
181
+ "full_attention",
182
+ "full_attention",
183
+ "full_attention",
184
+ "full_attention",
185
+ "full_attention",
186
+ "full_attention",
187
+ "full_attention",
188
+ "full_attention",
189
+ "full_attention",
190
+ "full_attention",
191
+ "full_attention",
192
+ "full_attention",
193
+ "full_attention",
194
+ "full_attention",
195
+ "full_attention",
196
+ "full_attention",
197
+ "full_attention"
198
+ ],
199
+ "max_position_embeddings": 40960,
200
+ "max_window_layers": 28,
201
+ "model_type": "qwen3",
202
+ "num_attention_heads": 16,
203
+ "num_hidden_layers": 28,
204
+ "num_key_value_heads": 8,
205
+ "rms_norm_eps": 1e-06,
206
+ "rope_scaling": null,
207
+ "rope_theta": 1000000,
208
+ "sliding_window": null,
209
+ "tie_word_embeddings": true,
210
+ "torch_dtype": "bfloat16",
211
+ "use_cache": true,
212
+ "use_sliding_window": false,
213
+ "vocab_size": 151681
214
+ },
215
+ "tie_word_embeddings": false,
216
+ "torch_dtype": "float16",
217
+ "transformers_version": "4.53.3",
218
+ "use_image_newline_parameter": true,
219
+ "video_token_index": 151680,
220
+ "vision_aspect_ratio": "anyres_max_9",
221
+ "vision_config": {
222
+ "attention_dropout": 0.0,
223
+ "hidden_act": "gelu_pytorch_tanh",
224
+ "hidden_size": 1152,
225
+ "image_size": 384,
226
+ "intermediate_size": 4304,
227
+ "layer_norm_eps": 1e-06,
228
+ "model_type": "siglip_vision_model",
229
+ "num_attention_heads": 16,
230
+ "num_channels": 3,
231
+ "num_hidden_layers": 26,
232
+ "patch_size": 16,
233
+ "vision_use_head": false
234
+ },
235
+ "vision_feature_layer": -1,
236
+ "vision_feature_select_strategy": "full"
237
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.53.3"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbf74c8a17e4c56b817a83b67d20d64b0956ebbdbc681be097192cb693609436
3
+ size 4248880912
preprocessor_config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_grid_pinpoints": [
8
+ [
9
+ 384,
10
+ 384
11
+ ],
12
+ [
13
+ 384,
14
+ 768
15
+ ],
16
+ [
17
+ 384,
18
+ 1152
19
+ ],
20
+ [
21
+ 384,
22
+ 1536
23
+ ],
24
+ [
25
+ 384,
26
+ 1920
27
+ ],
28
+ [
29
+ 384,
30
+ 2304
31
+ ],
32
+ [
33
+ 768,
34
+ 384
35
+ ],
36
+ [
37
+ 768,
38
+ 768
39
+ ],
40
+ [
41
+ 768,
42
+ 1152
43
+ ],
44
+ [
45
+ 768,
46
+ 1536
47
+ ],
48
+ [
49
+ 768,
50
+ 1920
51
+ ],
52
+ [
53
+ 768,
54
+ 2304
55
+ ],
56
+ [
57
+ 1152,
58
+ 384
59
+ ],
60
+ [
61
+ 1152,
62
+ 768
63
+ ],
64
+ [
65
+ 1152,
66
+ 1152
67
+ ],
68
+ [
69
+ 1152,
70
+ 1536
71
+ ],
72
+ [
73
+ 1152,
74
+ 1920
75
+ ],
76
+ [
77
+ 1152,
78
+ 2304
79
+ ],
80
+ [
81
+ 1536,
82
+ 384
83
+ ],
84
+ [
85
+ 1536,
86
+ 768
87
+ ],
88
+ [
89
+ 1536,
90
+ 1152
91
+ ],
92
+ [
93
+ 1536,
94
+ 1536
95
+ ],
96
+ [
97
+ 1536,
98
+ 1920
99
+ ],
100
+ [
101
+ 1536,
102
+ 2304
103
+ ],
104
+ [
105
+ 1920,
106
+ 384
107
+ ],
108
+ [
109
+ 1920,
110
+ 768
111
+ ],
112
+ [
113
+ 1920,
114
+ 1152
115
+ ],
116
+ [
117
+ 1920,
118
+ 1536
119
+ ],
120
+ [
121
+ 1920,
122
+ 1920
123
+ ],
124
+ [
125
+ 1920,
126
+ 2304
127
+ ],
128
+ [
129
+ 2304,
130
+ 384
131
+ ],
132
+ [
133
+ 2304,
134
+ 768
135
+ ],
136
+ [
137
+ 2304,
138
+ 1152
139
+ ],
140
+ [
141
+ 2304,
142
+ 1536
143
+ ],
144
+ [
145
+ 2304,
146
+ 1920
147
+ ],
148
+ [
149
+ 2304,
150
+ 2304
151
+ ]
152
+ ],
153
+ "image_mean": [
154
+ 0.5,
155
+ 0.5,
156
+ 0.5
157
+ ],
158
+ "image_processor_type": "LlavaOnevisionImageProcessor",
159
+ "image_std": [
160
+ 0.5,
161
+ 0.5,
162
+ 0.5
163
+ ],
164
+ "processor_class": "LlavaOnevisionProcessor",
165
+ "resample": 2,
166
+ "rescale_factor": 0.00392156862745098,
167
+ "size": {
168
+ "height": 384,
169
+ "width": 384
170
+ }
171
+ }
processor_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_token": "<image>",
3
+ "num_image_tokens": 576,
4
+ "processor_class": "LlavaOnevisionProcessor",
5
+ "video_token": "<video>",
6
+ "vision_aspect_ratio": "anyres_max_9",
7
+ "vision_feature_select_strategy": "full"
8
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<gro>",
4
+ "<ocr>",
5
+ "<char>",
6
+ "</char>",
7
+ "<obj>",
8
+ "</obj>",
9
+ "<bbox>",
10
+ "</bbox>",
11
+ "<delim>"
12
+ ],
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "[UNK]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be6a8990f1e9afb195f92b5408eb1ccc3c1a7baf263fe638b5a375b24b310524
3
+ size 11424851
tokenizer_config.json ADDED
@@ -0,0 +1,333 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "151669": {
214
+ "content": "[UNK]",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<gro>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<ocr>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<char>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "</char>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<obj>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "</obj>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "151676": {
270
+ "content": "<bbox>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "151677": {
278
+ "content": "</bbox>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "151678": {
286
+ "content": "<delim>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "151679": {
294
+ "content": "<image>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "151680": {
302
+ "content": "<video>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ }
309
+ },
310
+ "additional_special_tokens": [
311
+ "<gro>",
312
+ "<ocr>",
313
+ "<char>",
314
+ "</char>",
315
+ "<obj>",
316
+ "</obj>",
317
+ "<bbox>",
318
+ "</bbox>",
319
+ "<delim>"
320
+ ],
321
+ "bos_token": null,
322
+ "clean_up_tokenization_spaces": false,
323
+ "eos_token": "<|im_end|>",
324
+ "errors": "replace",
325
+ "extra_special_tokens": {},
326
+ "model_max_length": 16384,
327
+ "pad_token": "[UNK]",
328
+ "padding_side": "right",
329
+ "processor_class": "LlavaOnevisionProcessor",
330
+ "split_special_tokens": false,
331
+ "tokenizer_class": "Qwen2Tokenizer",
332
+ "unk_token": "[UNK]"
333
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": false,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": null,
8
+ "do_normalize": true,
9
+ "do_pad": null,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "do_sample_frames": false,
13
+ "fps": null,
14
+ "image_mean": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "image_processor_type": "SiglipImageProcessor",
20
+ "image_std": [
21
+ 0.5,
22
+ 0.5,
23
+ 0.5
24
+ ],
25
+ "input_data_format": null,
26
+ "num_frames": null,
27
+ "processor_class": "LlavaOnevisionProcessor",
28
+ "resample": 2,
29
+ "rescale_factor": 0.00392156862745098,
30
+ "size": {
31
+ "height": 384,
32
+ "width": 384
33
+ },
34
+ "size_divisor": null,
35
+ "video_metadata": null,
36
+ "video_processor_type": "LlavaOnevisionVideoProcessor"
37
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff