Hugging Face's logo

llava-hf
/
llava-onevision-qwen2-72b-ov-chat-hf

Image-Text-to-Text
Safetensors
English
Chinese
llava_onevision
vision
conversational
Model card Files Community
RaushanTurganbay HF staff commited on
Commit
46adefe
•
1 Parent(s): 2a8cda7

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +190 -0
config.json ADDED
@@ -0,0 +1,190 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 151646,
152
+ "model_type": "llava_onevision",
153
+ "projector_hidden_act": "gelu",
154
+ "text_config": {
155
+ "_name_or_path": "Qwen/Qwen2-72B-Instruct",
156
+ "architectures": [
157
+ "Qwen2ForCausalLM"
158
+ ],
159
+ "bos_token_id": 151643,
160
+ "eos_token_id": 151645,
161
+ "hidden_size": 8192,
162
+ "intermediate_size": 29568,
163
+ "max_window_layers": 80,
164
+ "model_type": "qwen2",
165
+ "num_attention_heads": 64,
166
+ "num_hidden_layers": 80,
167
+ "num_key_value_heads": 8,
168
+ "rope_theta": 1000000.0,
169
+ "torch_dtype": "bfloat16",
170
+ "vocab_size": 152128
171
+ },
172
+ "tie_word_embeddings": false,
173
+ "torch_dtype": "float16",
174
+ "transformers_version": "4.45.0.dev0",
175
+ "use_image_newline_parameter": true,
176
+ "video_token_index": 151647,
177
+ "vision_aspect_ratio": "anyres_max_9",
178
+ "vision_config": {
179
+ "hidden_size": 1152,
180
+ "image_size": 384,
181
+ "intermediate_size": 4304,
182
+ "model_type": "siglip_vision_model",
183
+ "num_attention_heads": 16,
184
+ "num_hidden_layers": 26,
185
+ "patch_size": 14,
186
+ "vision_use_head": false
187
+ },
188
+ "vision_feature_layer": -1,
189
+ "vision_feature_select_strategy": "full"
190
+ }