Hugging Face's logo

llava-hf
/
llava-onevision-qwen2-0.5b-ov-hf

Image-Text-to-Text
Transformers
ONNX
Safetensors
Transformers.js
English
Chinese
llava_onevision
image-to-text
vision
conversational
Model card Files
xet
Community
11
RaushanTurganbay HF Staff commited on
Commit
a70741f
·
verified ·
1 Parent(s): 36a89a6

Upload processor

Browse files
Files changed (7) hide show
  1. added_tokens.json +6 -0
  2. merges.txt +0 -0
  3. preprocessor_config.json +176 -0
  4. special_tokens_map.json +20 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +52 -0
  7. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<image>": 151646,
3
+ "<|endoftext|>": 151643,
4
+ "<|im_end|>": 151645,
5
+ "<|im_start|>": 151644
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 384,
4
+ "width": 384
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_pad": true,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "image_grid_pinpoints": [
13
+ [
14
+ 384,
15
+ 384
16
+ ],
17
+ [
18
+ 384,
19
+ 768
20
+ ],
21
+ [
22
+ 384,
23
+ 1152
24
+ ],
25
+ [
26
+ 384,
27
+ 1536
28
+ ],
29
+ [
30
+ 384,
31
+ 1920
32
+ ],
33
+ [
34
+ 384,
35
+ 2304
36
+ ],
37
+ [
38
+ 768,
39
+ 384
40
+ ],
41
+ [
42
+ 768,
43
+ 768
44
+ ],
45
+ [
46
+ 768,
47
+ 1152
48
+ ],
49
+ [
50
+ 768,
51
+ 1536
52
+ ],
53
+ [
54
+ 768,
55
+ 1920
56
+ ],
57
+ [
58
+ 768,
59
+ 2304
60
+ ],
61
+ [
62
+ 1152,
63
+ 384
64
+ ],
65
+ [
66
+ 1152,
67
+ 768
68
+ ],
69
+ [
70
+ 1152,
71
+ 1152
72
+ ],
73
+ [
74
+ 1152,
75
+ 1536
76
+ ],
77
+ [
78
+ 1152,
79
+ 1920
80
+ ],
81
+ [
82
+ 1152,
83
+ 2304
84
+ ],
85
+ [
86
+ 1536,
87
+ 384
88
+ ],
89
+ [
90
+ 1536,
91
+ 768
92
+ ],
93
+ [
94
+ 1536,
95
+ 1152
96
+ ],
97
+ [
98
+ 1536,
99
+ 1536
100
+ ],
101
+ [
102
+ 1536,
103
+ 1920
104
+ ],
105
+ [
106
+ 1536,
107
+ 2304
108
+ ],
109
+ [
110
+ 1920,
111
+ 384
112
+ ],
113
+ [
114
+ 1920,
115
+ 768
116
+ ],
117
+ [
118
+ 1920,
119
+ 1152
120
+ ],
121
+ [
122
+ 1920,
123
+ 1536
124
+ ],
125
+ [
126
+ 1920,
127
+ 1920
128
+ ],
129
+ [
130
+ 1920,
131
+ 2304
132
+ ],
133
+ [
134
+ 2304,
135
+ 384
136
+ ],
137
+ [
138
+ 2304,
139
+ 768
140
+ ],
141
+ [
142
+ 2304,
143
+ 1152
144
+ ],
145
+ [
146
+ 2304,
147
+ 1536
148
+ ],
149
+ [
150
+ 2304,
151
+ 1920
152
+ ],
153
+ [
154
+ 2304,
155
+ 2304
156
+ ]
157
+ ],
158
+ "image_mean": [
159
+ 0.5,
160
+ 0.5,
161
+ 0.5
162
+ ],
163
+ "image_processor_type": "LlavaNextImageProcessor",
164
+ "image_std": [
165
+ 0.5,
166
+ 0.5,
167
+ 0.5
168
+ ],
169
+ "processor_class": "LlavaNextProcessor",
170
+ "resample": 3,
171
+ "rescale_factor": 0.00392156862745098,
172
+ "size": {
173
+ "height": 384,
174
+ "width": 384
175
+ }
176
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<image>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "additional_special_tokens": [
38
+ "<|im_start|>",
39
+ "<|im_end|>"
40
+ ],
41
+ "bos_token": null,
42
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
43
+ "clean_up_tokenization_spaces": false,
44
+ "eos_token": "<|im_end|>",
45
+ "errors": "replace",
46
+ "model_max_length": 32768,
47
+ "pad_token": "<|endoftext|>",
48
+ "processor_class": "LlavaNextProcessor",
49
+ "split_special_tokens": false,
50
+ "tokenizer_class": "Qwen2Tokenizer",
51
+ "unk_token": null
52
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff