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
vision
conversational
Model card Files Community
10
RaushanTurganbay HF Staff commited on
Commit
6502c42
·
verified ·
1 Parent(s): c518e39

Create video_preprocessor_config.json

Browse files
Files changed (1) hide show
  1. video_preprocessor_config.json +228 -0
video_preprocessor_config.json ADDED
@@ -0,0 +1,228 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "do_sample_frames",
21
+ "video_metadata",
22
+ "fps",
23
+ "num_frames"
24
+ ],
25
+ "crop_size": null,
26
+ "data_format": "channels_first",
27
+ "default_to_square": false,
28
+ "device": null,
29
+ "do_center_crop": null,
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_pad": true,
33
+ "do_rescale": true,
34
+ "do_resize": true,
35
+ "do_sample_frames": false,
36
+ "fps": null,
37
+ "image_grid_pinpoints": [
38
+ [
39
+ 384,
40
+ 384
41
+ ],
42
+ [
43
+ 384,
44
+ 768
45
+ ],
46
+ [
47
+ 384,
48
+ 1152
49
+ ],
50
+ [
51
+ 384,
52
+ 1536
53
+ ],
54
+ [
55
+ 384,
56
+ 1920
57
+ ],
58
+ [
59
+ 384,
60
+ 2304
61
+ ],
62
+ [
63
+ 768,
64
+ 384
65
+ ],
66
+ [
67
+ 768,
68
+ 768
69
+ ],
70
+ [
71
+ 768,
72
+ 1152
73
+ ],
74
+ [
75
+ 768,
76
+ 1536
77
+ ],
78
+ [
79
+ 768,
80
+ 1920
81
+ ],
82
+ [
83
+ 768,
84
+ 2304
85
+ ],
86
+ [
87
+ 1152,
88
+ 384
89
+ ],
90
+ [
91
+ 1152,
92
+ 768
93
+ ],
94
+ [
95
+ 1152,
96
+ 1152
97
+ ],
98
+ [
99
+ 1152,
100
+ 1536
101
+ ],
102
+ [
103
+ 1152,
104
+ 1920
105
+ ],
106
+ [
107
+ 1152,
108
+ 2304
109
+ ],
110
+ [
111
+ 1536,
112
+ 384
113
+ ],
114
+ [
115
+ 1536,
116
+ 768
117
+ ],
118
+ [
119
+ 1536,
120
+ 1152
121
+ ],
122
+ [
123
+ 1536,
124
+ 1536
125
+ ],
126
+ [
127
+ 1536,
128
+ 1920
129
+ ],
130
+ [
131
+ 1536,
132
+ 2304
133
+ ],
134
+ [
135
+ 1920,
136
+ 384
137
+ ],
138
+ [
139
+ 1920,
140
+ 768
141
+ ],
142
+ [
143
+ 1920,
144
+ 1152
145
+ ],
146
+ [
147
+ 1920,
148
+ 1536
149
+ ],
150
+ [
151
+ 1920,
152
+ 1920
153
+ ],
154
+ [
155
+ 1920,
156
+ 2304
157
+ ],
158
+ [
159
+ 2304,
160
+ 384
161
+ ],
162
+ [
163
+ 2304,
164
+ 768
165
+ ],
166
+ [
167
+ 2304,
168
+ 1152
169
+ ],
170
+ [
171
+ 2304,
172
+ 1536
173
+ ],
174
+ [
175
+ 2304,
176
+ 1920
177
+ ],
178
+ [
179
+ 2304,
180
+ 2304
181
+ ]
182
+ ],
183
+ "image_mean": [
184
+ 0.5,
185
+ 0.5,
186
+ 0.5
187
+ ],
188
+ "image_std": [
189
+ 0.5,
190
+ 0.5,
191
+ 0.5
192
+ ],
193
+ "input_data_format": null,
194
+ "model_valid_processing_keys": [
195
+ "do_convert_rgb",
196
+ "do_resize",
197
+ "size",
198
+ "size_divisor",
199
+ "default_to_square",
200
+ "resample",
201
+ "do_rescale",
202
+ "rescale_factor",
203
+ "do_normalize",
204
+ "image_mean",
205
+ "image_std",
206
+ "do_pad",
207
+ "do_center_crop",
208
+ "crop_size",
209
+ "data_format",
210
+ "input_data_format",
211
+ "device",
212
+ "do_sample_frames",
213
+ "video_metadata",
214
+ "fps",
215
+ "num_frames"
216
+ ],
217
+ "num_frames": null,
218
+ "processor_class": "LlavaOnevisionProcessor",
219
+ "resample": 3,
220
+ "rescale_factor": 0.00392156862745098,
221
+ "size": {
222
+ "height": 384,
223
+ "width": 384
224
+ },
225
+ "size_divisor": null,
226
+ "video_metadata": null,
227
+ "video_processor_type": "LlavaOnevisionVideoProcessor"
228
+ }