Hugging Face's logo

cmp-nct
/
llava-1.6-gguf

Image-Text-to-Text
Transformers
GGUF
Inference Endpoints
Model card Files Community
10
cmp-nct commited on
Commit
3dc9bd9
•
1 Parent(s): 5bb00f4

Upload config.json

Browse files

config.json for the 336-14 VIT - required to compile a llava-1.6 projector

Files changed (1) hide show
  1. config.json +236 -0
config.json ADDED
@@ -0,0 +1,236 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/clip-vit-large-patch14-336",
3
+ "architectures": [
4
+ "CLIPModel"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 768,
10
+ "text_config": {
11
+ "_name_or_path": "",
12
+ "add_cross_attention": false,
13
+ "architectures": null,
14
+ "attention_dropout": 0.0,
15
+ "bad_words_ids": null,
16
+ "bos_token_id": 0,
17
+ "chunk_size_feed_forward": 0,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "dropout": 0.0,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 2,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "hidden_act": "quick_gelu",
31
+ "hidden_size": 768,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_factor": 1.0,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "is_decoder": false,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "layer_norm_eps": 1e-05,
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "max_position_embeddings": 77,
49
+ "min_length": 0,
50
+ "model_type": "clip_text_model",
51
+ "no_repeat_ngram_size": 0,
52
+ "num_attention_heads": 12,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_hidden_layers": 12,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 1,
61
+ "prefix": null,
62
+ "problem_type": null,
63
+ "projection_dim": 768,
64
+ "pruned_heads": {},
65
+ "remove_invalid_values": false,
66
+ "repetition_penalty": 1.0,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "sep_token_id": null,
70
+ "task_specific_params": null,
71
+ "temperature": 1.0,
72
+ "tf_legacy_loss": false,
73
+ "tie_encoder_decoder": false,
74
+ "tie_word_embeddings": true,
75
+ "tokenizer_class": null,
76
+ "top_k": 50,
77
+ "top_p": 1.0,
78
+ "torch_dtype": null,
79
+ "torchscript": false,
80
+ "transformers_version": "4.21.3",
81
+ "typical_p": 1.0,
82
+ "use_bfloat16": false,
83
+ "vocab_size": 49408
84
+ },
85
+ "text_config_dict": {
86
+ "hidden_size": 768,
87
+ "intermediate_size": 3072,
88
+ "num_attention_heads": 12,
89
+ "num_hidden_layers": 12,
90
+ "projection_dim": 768
91
+ },
92
+ "torch_dtype": "float32",
93
+ "transformers_version": null,
94
+ "vision_config": {
95
+ "_name_or_path": "",
96
+ "attention_dropout": 0.0,
97
+ "dropout": 0.0,
98
+ "hidden_act": "quick_gelu",
99
+ "hidden_size": 1024,
100
+ "image_size": 336,
101
+ "initializer_factor": 1.0,
102
+ "initializer_range": 0.02,
103
+ "intermediate_size": 4096,
104
+ "layer_norm_eps": 1e-05,
105
+ "model_type": "clip_vision_model",
106
+ "num_attention_heads": 16,
107
+ "num_channels": 3,
108
+ "num_hidden_layers": 24,
109
+ "patch_size": 14,
110
+ "projection_dim": 768,
111
+ "torch_dtype": "bfloat16",
112
+ "transformers_version": "4.31.0",
113
+ "image_aspect_ratio": "anyres",
114
+ "image_crop_resolution": 224,
115
+ "image_grid_pinpoints": [
116
+ [
117
+ 336,
118
+ 672
119
+ ],
120
+ [
121
+ 672,
122
+ 336
123
+ ],
124
+ [
125
+ 672,
126
+ 672
127
+ ],
128
+ [
129
+ 1008,
130
+ 336
131
+ ],
132
+ [
133
+ 336,
134
+ 1008
135
+ ]
136
+ ],
137
+ "mm_patch_merge_type": "spatial_unpad",
138
+ "image_split_resolution": 224,
139
+ "initializer_range": 0.02,
140
+ "max_length": 4096,
141
+ "max_position_embeddings": 4096,
142
+ "mm_hidden_size": 1024,
143
+ "mm_projector_lr": null,
144
+ "mm_projector_type": "mlp2x_gelu",
145
+ "mm_resampler_type": null,
146
+ "mm_use_im_patch_token": false,
147
+ "mm_use_im_start_end": false,
148
+ "mm_vision_select_feature": "patch",
149
+ "mm_vision_select_layer": -2,
150
+ "mm_vision_tower__": "openai/clip-vit-large-patch14-336",
151
+ "mm_vision_tower_lr": 2e-06,
152
+ "XX": 0,
153
+ "add_cross_attention": false,
154
+ "architectures": null,
155
+ "attention_dropout": 0.0,
156
+ "bad_words_ids": null,
157
+ "bos_token_id": null,
158
+ "chunk_size_feed_forward": 0,
159
+ "cross_attention_hidden_size": null,
160
+ "decoder_start_token_id": null,
161
+ "diversity_penalty": 0.0,
162
+ "do_sample": false,
163
+ "dropout": 0.0,
164
+ "early_stopping": false,
165
+ "encoder_no_repeat_ngram_size": 0,
166
+ "eos_token_id": null,
167
+ "exponential_decay_length_penalty": null,
168
+ "finetuning_task": null,
169
+ "forced_bos_token_id": null,
170
+ "forced_eos_token_id": null,
171
+ "hidden_act": "quick_gelu",
172
+ "hidden_size": 1024,
173
+ "id2label": {
174
+ "0": "LABEL_0",
175
+ "1": "LABEL_1"
176
+ },
177
+ "image_size": 336,
178
+ "initializer_factor": 1.0,
179
+ "initializer_range": 0.02,
180
+ "intermediate_size": 4096,
181
+ "is_decoder": false,
182
+ "is_encoder_decoder": false,
183
+ "label2id": {
184
+ "LABEL_0": 0,
185
+ "LABEL_1": 1
186
+ },
187
+ "layer_norm_eps": 1e-05,
188
+ "length_penalty": 1.0,
189
+ "max_length": 20,
190
+ "min_length": 0,
191
+ "model_type": "clip_vision_model",
192
+ "no_repeat_ngram_size": 0,
193
+ "num_attention_heads": 16,
194
+ "num_beam_groups": 1,
195
+ "num_beams": 1,
196
+ "num_channels": 3,
197
+ "num_hidden_layers": 24,
198
+ "num_return_sequences": 1,
199
+ "output_attentions": false,
200
+ "output_hidden_states": false,
201
+ "output_scores": false,
202
+ "pad_token_id": null,
203
+ "patch_size": 14,
204
+ "prefix": null,
205
+ "problem_type": null,
206
+ "projection_dim": 768,
207
+ "pruned_heads": {},
208
+ "remove_invalid_values": false,
209
+ "repetition_penalty": 1.0,
210
+ "return_dict": true,
211
+ "return_dict_in_generate": false,
212
+ "sep_token_id": null,
213
+ "task_specific_params": null,
214
+ "temperature": 1.0,
215
+ "tf_legacy_loss": false,
216
+ "tie_encoder_decoder": false,
217
+ "tie_word_embeddings": true,
218
+ "tokenizer_class": null,
219
+ "top_k": 50,
220
+ "top_p": 1.0,
221
+ "torch_dtype": null,
222
+ "torchscript": false,
223
+ "transformers_version": "4.21.3",
224
+ "typical_p": 1.0,
225
+ "use_bfloat16": false
226
+ },
227
+ "vision_config_dict": {
228
+ "hidden_size": 1024,
229
+ "image_size": 336,
230
+ "intermediate_size": 4096,
231
+ "num_attention_heads": 16,
232
+ "num_hidden_layers": 24,
233
+ "patch_size": 14,
234
+ "projection_dim": 768
235
+ }
236
+ }