config.json
4.5 KB · 175 lines · json Raw
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 "exponential_decay_length_penalty": null,
26 "finetuning_task": null,
27 "forced_bos_token_id": null,
28 "forced_eos_token_id": null,
29 "hidden_act": "gelu",
30 "hidden_size": 768,
31 "id2label": {
32 "0": "LABEL_0",
33 "1": "LABEL_1"
34 },
35 "initializer_factor": 1.0,
36 "initializer_range": 0.02,
37 "intermediate_size": 3072,
38 "is_decoder": false,
39 "is_encoder_decoder": false,
40 "label2id": {
41 "LABEL_0": 0,
42 "LABEL_1": 1
43 },
44 "layer_norm_eps": 1e-05,
45 "length_penalty": 1.0,
46 "max_length": 20,
47 "max_position_embeddings": 77,
48 "min_length": 0,
49 "model_type": "clip_text_model",
50 "no_repeat_ngram_size": 0,
51 "num_attention_heads": 12,
52 "num_beam_groups": 1,
53 "num_beams": 1,
54 "num_hidden_layers": 12,
55 "num_return_sequences": 1,
56 "output_attentions": false,
57 "output_hidden_states": false,
58 "output_scores": false,
59 "pad_token_id": 1,
60 "prefix": null,
61 "problem_type": null,
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 "tf_legacy_loss": false,
71 "tie_encoder_decoder": false,
72 "tie_word_embeddings": true,
73 "tokenizer_class": null,
74 "top_k": 50,
75 "top_p": 1.0,
76 "torch_dtype": null,
77 "torchscript": false,
78 "transformers_version": "4.21.3",
79 "typical_p": 1.0,
80 "use_bfloat16": false,
81 "vocab_size": 49408
82 },
83 "text_config_dict": {
84 "hidden_act": "gelu",
85 "hidden_size": 768,
86 "intermediate_size": 3072,
87 "num_attention_heads": 12
88 },
89 "torch_dtype": "float32",
90 "transformers_version": null,
91 "vision_config": {
92 "_name_or_path": "",
93 "add_cross_attention": false,
94 "architectures": null,
95 "attention_dropout": 0.0,
96 "bad_words_ids": null,
97 "bos_token_id": null,
98 "chunk_size_feed_forward": 0,
99 "cross_attention_hidden_size": null,
100 "decoder_start_token_id": null,
101 "diversity_penalty": 0.0,
102 "do_sample": false,
103 "dropout": 0.0,
104 "early_stopping": false,
105 "encoder_no_repeat_ngram_size": 0,
106 "eos_token_id": null,
107 "exponential_decay_length_penalty": null,
108 "finetuning_task": null,
109 "forced_bos_token_id": null,
110 "forced_eos_token_id": null,
111 "hidden_act": "gelu",
112 "hidden_size": 1024,
113 "id2label": {
114 "0": "LABEL_0",
115 "1": "LABEL_1"
116 },
117 "image_size": 224,
118 "initializer_factor": 1.0,
119 "initializer_range": 0.02,
120 "intermediate_size": 4096,
121 "is_decoder": false,
122 "is_encoder_decoder": false,
123 "label2id": {
124 "LABEL_0": 0,
125 "LABEL_1": 1
126 },
127 "layer_norm_eps": 1e-05,
128 "length_penalty": 1.0,
129 "max_length": 20,
130 "min_length": 0,
131 "model_type": "clip_vision_model",
132 "no_repeat_ngram_size": 0,
133 "num_attention_heads": 16,
134 "num_beam_groups": 1,
135 "num_beams": 1,
136 "num_channels": 3,
137 "num_hidden_layers": 24,
138 "num_return_sequences": 1,
139 "output_attentions": false,
140 "output_hidden_states": false,
141 "output_scores": false,
142 "pad_token_id": null,
143 "patch_size": 14,
144 "prefix": null,
145 "problem_type": null,
146 "pruned_heads": {},
147 "remove_invalid_values": false,
148 "repetition_penalty": 1.0,
149 "return_dict": true,
150 "return_dict_in_generate": false,
151 "sep_token_id": null,
152 "task_specific_params": null,
153 "temperature": 1.0,
154 "tf_legacy_loss": false,
155 "tie_encoder_decoder": false,
156 "tie_word_embeddings": true,
157 "tokenizer_class": null,
158 "top_k": 50,
159 "top_p": 1.0,
160 "torch_dtype": null,
161 "torchscript": false,
162 "transformers_version": "4.21.3",
163 "typical_p": 1.0,
164 "use_bfloat16": false
165 },
166 "vision_config_dict": {
167 "hidden_act": "gelu",
168 "hidden_size": 1024,
169 "intermediate_size": 4096,
170 "num_attention_heads": 16,
171 "num_hidden_layers": 24,
172 "patch_size": 14
173 }
174 }
175