Hugging Face's logo

0914eagle
/
ViT14_emotic_finetuning

Zero-Shot Image Classification
Transformers
PyTorch
clip
Model card Files
xet
 Community
1
0914eagle commited on
Commit
a74dd81
·
verified ·
1 Parent(s): e97fdd7

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +168 -7
config.json CHANGED
@@ -1,9 +1,170 @@
1
  {
2
- "architectures": ["CLIPModel"],
3
- "model_type": "clip",
4
- "model_name": "ViT-L/14",
5
- "device": "cuda",
6
- "input_resolution": 224,
7
- "context_length": 77,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "vocab_size": 49408
9
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "CLIPModel"
4
+ ],
5
+ "initializer_factor": 1.0,
6
+ "logit_scale_init_value": 2.6592,
7
+ "model_type": "clip",
8
+ "projection_dim": 768,
9
+ "text_config": {
10
+ "_name_or_path": "",
11
+ "add_cross_attention": false,
12
+ "architectures": null,
13
+ "attention_dropout": 0.0,
14
+ "bad_words_ids": null,
15
+ "bos_token_id": 0,
16
+ "chunk_size_feed_forward": 0,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "dropout": 0.0,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": 2,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "hidden_act": "quick_gelu",
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_factor": 1.0,
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "is_decoder": false,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1
42
+ },
43
+ "layer_norm_eps": 1e-05,
44
+ "length_penalty": 1.0,
45
+ "max_length": 20,
46
+ "max_position_embeddings": 77,
47
+ "min_length": 0,
48
+ "model_type": "clip_text_model",
49
+ "no_repeat_ngram_size": 0,
50
+ "num_attention_heads": 12,
51
+ "num_beam_groups": 1,
52
+ "num_beams": 1,
53
+ "num_hidden_layers": 12,
54
+ "num_return_sequences": 1,
55
+ "output_attentions": false,
56
+ "output_hidden_states": false,
57
+ "output_scores": false,
58
+ "pad_token_id": 1,
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "projection_dim" : 768,
62
+ "pruned_heads": {},
63
+ "remove_invalid_values": false,
64
+ "repetition_penalty": 1.0,
65
+ "return_dict": true,
66
+ "return_dict_in_generate": false,
67
+ "sep_token_id": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": true,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": null,
76
+ "torchscript": false,
77
+ "transformers_version": "4.16.0.dev0",
78
+ "use_bfloat16": false,
79
  "vocab_size": 49408
80
+ },
81
+ "text_config_dict": {
82
+ "hidden_size": 768,
83
+ "intermediate_size": 3072,
84
+ "num_attention_heads": 12,
85
+ "num_hidden_layers": 12,
86
+ "projection_dim": 768
87
+ },
88
+ "torch_dtype": "float32",
89
+ "transformers_version": null,
90
+ "vision_config": {
91
+ "_name_or_path": "",
92
+ "add_cross_attention": false,
93
+ "architectures": null,
94
+ "attention_dropout": 0.0,
95
+ "bad_words_ids": null,
96
+ "bos_token_id": null,
97
+ "chunk_size_feed_forward": 0,
98
+ "cross_attention_hidden_size": null,
99
+ "decoder_start_token_id": null,
100
+ "diversity_penalty": 0.0,
101
+ "do_sample": false,
102
+ "dropout": 0.0,
103
+ "early_stopping": false,
104
+ "encoder_no_repeat_ngram_size": 0,
105
+ "eos_token_id": null,
106
+ "finetuning_task": null,
107
+ "forced_bos_token_id": null,
108
+ "forced_eos_token_id": null,
109
+ "hidden_act": "quick_gelu",
110
+ "hidden_size": 1024,
111
+ "id2label": {
112
+ "0": "LABEL_0",
113
+ "1": "LABEL_1"
114
+ },
115
+ "image_size": 224,
116
+ "initializer_factor": 1.0,
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 4096,
119
+ "is_decoder": false,
120
+ "is_encoder_decoder": false,
121
+ "label2id": {
122
+ "LABEL_0": 0,
123
+ "LABEL_1": 1
124
+ },
125
+ "layer_norm_eps": 1e-05,
126
+ "length_penalty": 1.0,
127
+ "max_length": 20,
128
+ "min_length": 0,
129
+ "model_type": "clip_vision_model",
130
+ "no_repeat_ngram_size": 0,
131
+ "num_attention_heads": 16,
132
+ "num_beam_groups": 1,
133
+ "num_beams": 1,
134
+ "num_hidden_layers": 24,
135
+ "num_return_sequences": 1,
136
+ "output_attentions": false,
137
+ "output_hidden_states": false,
138
+ "output_scores": false,
139
+ "pad_token_id": null,
140
+ "patch_size": 14,
141
+ "prefix": null,
142
+ "problem_type": null,
143
+ "projection_dim" : 768,
144
+ "pruned_heads": {},
145
+ "remove_invalid_values": false,
146
+ "repetition_penalty": 1.0,
147
+ "return_dict": true,
148
+ "return_dict_in_generate": false,
149
+ "sep_token_id": null,
150
+ "task_specific_params": null,
151
+ "temperature": 1.0,
152
+ "tie_encoder_decoder": false,
153
+ "tie_word_embeddings": true,
154
+ "tokenizer_class": null,
155
+ "top_k": 50,
156
+ "top_p": 1.0,
157
+ "torch_dtype": null,
158
+ "torchscript": false,
159
+ "transformers_version": "4.16.0.dev0",
160
+ "use_bfloat16": false
161
+ },
162
+ "vision_config_dict": {
163
+ "hidden_size": 1024,
164
+ "intermediate_size": 4096,
165
+ "num_attention_heads": 16,
166
+ "num_hidden_layers": 24,
167
+ "patch_size": 14,
168
+ "projection_dim": 768
169
+ }
170
+ }