x54-729 commited on
Commit
059a269
1 Parent(s): e67ed29

remove clip

Browse files
clip_l_560_pro7b/config.json DELETED
@@ -1,178 +0,0 @@
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": "quick_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
- "projection_dim": 768,
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
- "tf_legacy_loss": false,
72
- "tie_encoder_decoder": false,
73
- "tie_word_embeddings": true,
74
- "tokenizer_class": null,
75
- "top_k": 50,
76
- "top_p": 1.0,
77
- "torch_dtype": null,
78
- "torchscript": false,
79
- "transformers_version": "4.21.3",
80
- "typical_p": 1.0,
81
- "use_bfloat16": false,
82
- "vocab_size": 49408
83
- },
84
- "text_config_dict": {
85
- "hidden_size": 768,
86
- "intermediate_size": 3072,
87
- "num_attention_heads": 12,
88
- "num_hidden_layers": 12,
89
- "projection_dim": 768
90
- },
91
- "torch_dtype": "float32",
92
- "transformers_version": null,
93
- "vision_config": {
94
- "_name_or_path": "",
95
- "add_cross_attention": false,
96
- "architectures": null,
97
- "attention_dropout": 0.0,
98
- "bad_words_ids": null,
99
- "bos_token_id": null,
100
- "chunk_size_feed_forward": 0,
101
- "cross_attention_hidden_size": null,
102
- "decoder_start_token_id": null,
103
- "diversity_penalty": 0.0,
104
- "do_sample": false,
105
- "dropout": 0.0,
106
- "early_stopping": false,
107
- "encoder_no_repeat_ngram_size": 0,
108
- "eos_token_id": null,
109
- "exponential_decay_length_penalty": null,
110
- "finetuning_task": null,
111
- "forced_bos_token_id": null,
112
- "forced_eos_token_id": null,
113
- "hidden_act": "quick_gelu",
114
- "hidden_size": 1024,
115
- "id2label": {
116
- "0": "LABEL_0",
117
- "1": "LABEL_1"
118
- },
119
- "image_size": 560,
120
- "initializer_factor": 1.0,
121
- "initializer_range": 0.02,
122
- "intermediate_size": 4096,
123
- "is_decoder": false,
124
- "is_encoder_decoder": false,
125
- "label2id": {
126
- "LABEL_0": 0,
127
- "LABEL_1": 1
128
- },
129
- "layer_norm_eps": 1e-05,
130
- "length_penalty": 1.0,
131
- "max_length": 20,
132
- "min_length": 0,
133
- "model_type": "clip_vision_model",
134
- "no_repeat_ngram_size": 0,
135
- "num_attention_heads": 16,
136
- "num_beam_groups": 1,
137
- "num_beams": 1,
138
- "num_channels": 3,
139
- "num_hidden_layers": 24,
140
- "num_return_sequences": 1,
141
- "output_attentions": false,
142
- "output_hidden_states": false,
143
- "output_scores": false,
144
- "pad_token_id": null,
145
- "patch_size": 14,
146
- "prefix": null,
147
- "problem_type": null,
148
- "projection_dim": 768,
149
- "pruned_heads": {},
150
- "remove_invalid_values": false,
151
- "repetition_penalty": 1.0,
152
- "return_dict": true,
153
- "return_dict_in_generate": false,
154
- "sep_token_id": null,
155
- "task_specific_params": null,
156
- "temperature": 1.0,
157
- "tf_legacy_loss": false,
158
- "tie_encoder_decoder": false,
159
- "tie_word_embeddings": true,
160
- "tokenizer_class": null,
161
- "top_k": 50,
162
- "top_p": 1.0,
163
- "torch_dtype": null,
164
- "torchscript": false,
165
- "transformers_version": "4.21.3",
166
- "typical_p": 1.0,
167
- "use_bfloat16": false
168
- },
169
- "vision_config_dict": {
170
- "hidden_size": 1024,
171
- "image_size": 560,
172
- "intermediate_size": 4096,
173
- "num_attention_heads": 16,
174
- "num_hidden_layers": 24,
175
- "patch_size": 14,
176
- "projection_dim": 768
177
- }
178
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
clip_l_560_pro7b/preprocessor_config.json DELETED
@@ -1,19 +0,0 @@
1
- {
2
- "crop_size": 560,
3
- "do_center_crop": true,
4
- "do_normalize": true,
5
- "do_resize": true,
6
- "feature_extractor_type": "CLIPFeatureExtractor",
7
- "image_mean": [
8
- 0.48145466,
9
- 0.4578275,
10
- 0.40821073
11
- ],
12
- "image_std": [
13
- 0.26862954,
14
- 0.26130258,
15
- 0.27577711
16
- ],
17
- "resample": 3,
18
- "size": 560
19
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
clip_l_560_pro7b/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebc457eed8d8cd5c6730808fc545ce192a859f8a9d2608f729b2b0a6baf0b836
3
- size 1107085581