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
ffa02c4
•
1 Parent(s): 55c82be

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +180 -42
config.json CHANGED
@@ -1,62 +1,200 @@
1
  {
2
- "_name_or_path": "vit-large336-custom",
3
  "architectures": [
4
- "CLIPVisionModel"
5
  ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "attention_dropout": 0.0,
7
  "dropout": 0.0,
8
  "hidden_act": "quick_gelu",
9
- "hidden_size": 1024,
10
- "image_size": 336,
11
- "initializer_factor": 1.0,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 4096,
14
- "layer_norm_eps": 1e-05,
15
- "model_type": "clip_vision_model",
16
- "num_attention_heads": 16,
17
- "num_channels": 3,
18
- "num_hidden_layers": 24,
19
- "patch_size": 14,
20
- "projection_dim": 768,
21
- "torch_dtype": "bfloat16",
22
- "transformers_version": "4.31.0",
23
- "image_aspect_ratio": "anyres",
24
- "image_crop_resolution": 224,
25
- "image_grid_pinpoints": [
26
- [
27
- 336,
28
- 672
29
- ],
30
- [
31
- 672,
32
- 336
33
- ],
34
- [
35
- 672,
36
- 672
37
- ],
38
- [
39
- 1008,
40
- 336
41
- ],
42
- [
43
- 336,
44
  1008
45
  ]
46
  ],
 
47
  "image_split_resolution": 224,
48
  "initializer_range": 0.02,
49
  "max_length": 4096,
50
  "max_position_embeddings": 4096,
51
  "mm_hidden_size": 1024,
52
- "mm_patch_merge_type": "spatial_unpad",
53
  "mm_projector_lr": null,
54
  "mm_projector_type": "mlp2x_gelu",
55
  "mm_resampler_type": null,
56
- "mm_use_im_patch_token": false,
57
- "mm_use_im_start_end": false,
58
  "mm_vision_select_feature": "patch",
59
  "mm_vision_select_layer": -2,
60
  "mm_vision_tower__": "openai/clip-vit-large-patch14-336",
61
- "mm_vision_tower_lr": 2e-06
62
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
  1008
100
  ]
101
  ],
102
+ "mm_patch_merge_type": "spatial_unpad",
103
  "image_split_resolution": 224,
104
  "initializer_range": 0.02,
105
  "max_length": 4096,
106
  "max_position_embeddings": 4096,
107
  "mm_hidden_size": 1024,
108
+
109
  "mm_projector_lr": null,
110
  "mm_projector_type": "mlp2x_gelu",
111
  "mm_resampler_type": null,
 
 
112
  "mm_vision_select_feature": "patch",
113
  "mm_vision_select_layer": -2,
114
  "mm_vision_tower__": "openai/clip-vit-large-patch14-336",
115
+ "mm_vision_tower_lr": 2e-06,
116
+ "XX": 0,
117
+ "add_cross_attention": false,
118
+ "architectures": null,
119
+ "attention_dropout": 0.0,
120
+ "bad_words_ids": null,
121
+ "bos_token_id": null,
122
+ "chunk_size_feed_forward": 0,
123
+ "cross_attention_hidden_size": null,
124
+ "decoder_start_token_id": null,
125
+ "diversity_penalty": 0.0,
126
+ "do_sample": false,
127
+ "dropout": 0.0,
128
+ "early_stopping": false,
129
+ "encoder_no_repeat_ngram_size": 0,
130
+ "eos_token_id": null,
131
+ "exponential_decay_length_penalty": null,
132
+ "finetuning_task": null,
133
+ "forced_bos_token_id": null,
134
+ "forced_eos_token_id": null,
135
+ "hidden_act": "quick_gelu",
136
+ "hidden_size": 1024,
137
+ "id2label": {
138
+ "0": "LABEL_0",
139
+ "1": "LABEL_1"
140
+ },
141
+ "image_size": 336,
142
+ "initializer_factor": 1.0,
143
+ "initializer_range": 0.02,
144
+ "intermediate_size": 4096,
145
+ "is_decoder": false,
146
+ "is_encoder_decoder": false,
147
+ "label2id": {
148
+ "LABEL_0": 0,
149
+ "LABEL_1": 1
150
+ },
151
+ "layer_norm_eps": 1e-05,
152
+ "length_penalty": 1.0,
153
+ "max_length": 20,
154
+ "min_length": 0,
155
+ "model_type": "clip_vision_model",
156
+ "no_repeat_ngram_size": 0,
157
+ "num_attention_heads": 16,
158
+ "num_beam_groups": 1,
159
+ "num_beams": 1,
160
+ "num_channels": 3,
161
+ "num_hidden_layers": 24,
162
+ "num_return_sequences": 1,
163
+ "output_attentions": false,
164
+ "output_hidden_states": false,
165
+ "output_scores": false,
166
+ "pad_token_id": null,
167
+ "patch_size": 14,
168
+ "prefix": null,
169
+ "problem_type": null,
170
+ "projection_dim": 768,
171
+ "pruned_heads": {},
172
+ "remove_invalid_values": false,
173
+ "repetition_penalty": 1.0,
174
+ "return_dict": true,
175
+ "return_dict_in_generate": false,
176
+ "sep_token_id": null,
177
+ "task_specific_params": null,
178
+ "temperature": 1.0,
179
+ "tf_legacy_loss": false,
180
+ "tie_encoder_decoder": false,
181
+ "tie_word_embeddings": true,
182
+ "tokenizer_class": null,
183
+ "top_k": 50,
184
+ "top_p": 1.0,
185
+ "torch_dtype": null,
186
+ "torchscript": false,
187
+ "transformers_version": "4.21.3",
188
+ "typical_p": 1.0,
189
+ "use_bfloat16": false
190
+ },
191
+ "vision_config_dict": {
192
+ "hidden_size": 1024,
193
+ "image_size": 336,
194
+ "intermediate_size": 4096,
195
+ "num_attention_heads": 16,
196
+ "num_hidden_layers": 24,
197
+ "patch_size": 14,
198
+ "projection_dim": 768
199
+ }
200
+ }