config.json
4.1 KB · 158 lines · json Raw
1 {
2 "_name_or_path": "openai/clip-vit-base-patch32",
3 "architectures": [
4 "CLIPModel"
5 ],
6 "initializer_factor": 1.0,
7 "logit_scale_init_value": 2.6592,
8 "model_type": "clip",
9 "projection_dim": 512,
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 "finetuning_task": null,
27 "forced_bos_token_id": null,
28 "forced_eos_token_id": null,
29 "hidden_act": "quick_gelu",
30 "hidden_size": 512,
31 "id2label": {
32 "0": "LABEL_0",
33 "1": "LABEL_1"
34 },
35 "initializer_factor": 1.0,
36 "initializer_range": 0.02,
37 "intermediate_size": 2048,
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": 8,
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 "projection_dim": 512,
62 "problem_type": null,
63 "pruned_heads": {},
64 "remove_invalid_values": false,
65 "repetition_penalty": 1.0,
66 "return_dict": true,
67 "return_dict_in_generate": false,
68 "sep_token_id": null,
69 "task_specific_params": null,
70 "temperature": 1.0,
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": "4.16.0.dev0",
79 "use_bfloat16": false,
80 "vocab_size": 49408
81 },
82 "text_config_dict": null,
83 "transformers_version": null,
84 "vision_config": {
85 "_name_or_path": "",
86 "add_cross_attention": false,
87 "architectures": null,
88 "attention_dropout": 0.0,
89 "bad_words_ids": null,
90 "bos_token_id": null,
91 "chunk_size_feed_forward": 0,
92 "cross_attention_hidden_size": null,
93 "decoder_start_token_id": null,
94 "diversity_penalty": 0.0,
95 "do_sample": false,
96 "dropout": 0.0,
97 "early_stopping": false,
98 "encoder_no_repeat_ngram_size": 0,
99 "eos_token_id": null,
100 "finetuning_task": null,
101 "forced_bos_token_id": null,
102 "forced_eos_token_id": null,
103 "hidden_act": "quick_gelu",
104 "hidden_size": 768,
105 "id2label": {
106 "0": "LABEL_0",
107 "1": "LABEL_1"
108 },
109 "image_size": 224,
110 "initializer_factor": 1.0,
111 "initializer_range": 0.02,
112 "intermediate_size": 3072,
113 "is_decoder": false,
114 "is_encoder_decoder": false,
115 "label2id": {
116 "LABEL_0": 0,
117 "LABEL_1": 1
118 },
119 "layer_norm_eps": 1e-05,
120 "length_penalty": 1.0,
121 "max_length": 20,
122 "min_length": 0,
123 "model_type": "clip_vision_model",
124 "no_repeat_ngram_size": 0,
125 "num_attention_heads": 12,
126 "num_beam_groups": 1,
127 "num_beams": 1,
128 "num_hidden_layers": 12,
129 "num_return_sequences": 1,
130 "output_attentions": false,
131 "output_hidden_states": false,
132 "output_scores": false,
133 "pad_token_id": null,
134 "patch_size": 32,
135 "prefix": null,
136 "projection_dim" : 512,
137 "problem_type": null,
138 "pruned_heads": {},
139 "remove_invalid_values": false,
140 "repetition_penalty": 1.0,
141 "return_dict": true,
142 "return_dict_in_generate": false,
143 "sep_token_id": null,
144 "task_specific_params": null,
145 "temperature": 1.0,
146 "tie_encoder_decoder": false,
147 "tie_word_embeddings": true,
148 "tokenizer_class": null,
149 "top_k": 50,
150 "top_p": 1.0,
151 "torch_dtype": null,
152 "torchscript": false,
153 "transformers_version": "4.16.0.dev0",
154 "use_bfloat16": false
155 },
156 "vision_config_dict": null
157 }
158