Hugging Face's logo

hf-internal-testing
/
tiny-random-clip

Transformers
PyTorch
clip
Model card Files
xet
Community
4
lysandre HF Staff commited on
Commit
53fb674
·
1 Parent(s): 3984679

Add model and configuration.

Browse files
Files changed (2) hide show
  1. config.json +292 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,292 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "initializer_factor": 1.0,
3
+ "model_type": "clip",
4
+ "projection_dim": 64,
5
+ "text_config": {
6
+ "_name_or_path": "",
7
+ "add_cross_attention": false,
8
+ "architectures": null,
9
+ "attention_dropout": 0.1,
10
+ "bad_words_ids": null,
11
+ "bos_token_id": 0,
12
+ "chunk_size_feed_forward": 0,
13
+ "decoder_start_token_id": null,
14
+ "diversity_penalty": 0.0,
15
+ "do_sample": false,
16
+ "dropout": 0.1,
17
+ "early_stopping": false,
18
+ "encoder_no_repeat_ngram_size": 0,
19
+ "eos_token_id": 2,
20
+ "finetuning_task": null,
21
+ "forced_bos_token_id": null,
22
+ "forced_eos_token_id": null,
23
+ "gradient_checkpointing": false,
24
+ "hidden_act": "quick_gelu",
25
+ "hidden_size": 32,
26
+ "id2label": {
27
+ "0": "LABEL_0",
28
+ "1": "LABEL_1"
29
+ },
30
+ "initializer_factor": 1.0,
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 37,
33
+ "is_decoder": false,
34
+ "is_encoder_decoder": false,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1
38
+ },
39
+ "layer_norm_eps": 1e-05,
40
+ "length_penalty": 1.0,
41
+ "max_length": 20,
42
+ "max_position_embeddings": 512,
43
+ "min_length": 0,
44
+ "model_type": "clip_text_model",
45
+ "no_repeat_ngram_size": 0,
46
+ "num_attention_heads": 4,
47
+ "num_beam_groups": 1,
48
+ "num_beams": 1,
49
+ "num_hidden_layers": 5,
50
+ "num_return_sequences": 1,
51
+ "output_attentions": false,
52
+ "output_hidden_states": false,
53
+ "output_scores": false,
54
+ "pad_token_id": 1,
55
+ "prefix": null,
56
+ "problem_type": null,
57
+ "pruned_heads": {},
58
+ "remove_invalid_values": false,
59
+ "repetition_penalty": 1.0,
60
+ "return_dict": true,
61
+ "return_dict_in_generate": false,
62
+ "sep_token_id": null,
63
+ "task_specific_params": null,
64
+ "temperature": 1.0,
65
+ "tie_encoder_decoder": false,
66
+ "tie_word_embeddings": true,
67
+ "tokenizer_class": null,
68
+ "top_k": 50,
69
+ "top_p": 1.0,
70
+ "torch_dtype": null,
71
+ "torchscript": false,
72
+ "transformers_version": "4.10.0.dev0",
73
+ "use_bfloat16": false,
74
+ "vocab_size": 99
75
+ },
76
+ "text_config_dict": {
77
+ "_name_or_path": "",
78
+ "add_cross_attention": false,
79
+ "architectures": null,
80
+ "attention_dropout": 0.1,
81
+ "bad_words_ids": null,
82
+ "bos_token_id": 0,
83
+ "chunk_size_feed_forward": 0,
84
+ "decoder_start_token_id": null,
85
+ "diversity_penalty": 0.0,
86
+ "do_sample": false,
87
+ "dropout": 0.1,
88
+ "early_stopping": false,
89
+ "encoder_no_repeat_ngram_size": 0,
90
+ "eos_token_id": 2,
91
+ "finetuning_task": null,
92
+ "forced_bos_token_id": null,
93
+ "forced_eos_token_id": null,
94
+ "gradient_checkpointing": false,
95
+ "hidden_act": "quick_gelu",
96
+ "hidden_size": 32,
97
+ "id2label": {
98
+ "0": "LABEL_0",
99
+ "1": "LABEL_1"
100
+ },
101
+ "initializer_factor": 1.0,
102
+ "initializer_range": 0.02,
103
+ "intermediate_size": 37,
104
+ "is_decoder": false,
105
+ "is_encoder_decoder": false,
106
+ "label2id": {
107
+ "LABEL_0": 0,
108
+ "LABEL_1": 1
109
+ },
110
+ "layer_norm_eps": 1e-05,
111
+ "length_penalty": 1.0,
112
+ "max_length": 20,
113
+ "max_position_embeddings": 512,
114
+ "min_length": 0,
115
+ "model_type": "clip_text_model",
116
+ "no_repeat_ngram_size": 0,
117
+ "num_attention_heads": 4,
118
+ "num_beam_groups": 1,
119
+ "num_beams": 1,
120
+ "num_hidden_layers": 5,
121
+ "num_return_sequences": 1,
122
+ "output_attentions": false,
123
+ "output_hidden_states": false,
124
+ "output_scores": false,
125
+ "pad_token_id": 1,
126
+ "prefix": null,
127
+ "problem_type": null,
128
+ "pruned_heads": {},
129
+ "remove_invalid_values": false,
130
+ "repetition_penalty": 1.0,
131
+ "return_dict": true,
132
+ "return_dict_in_generate": false,
133
+ "sep_token_id": null,
134
+ "task_specific_params": null,
135
+ "temperature": 1.0,
136
+ "tie_encoder_decoder": false,
137
+ "tie_word_embeddings": true,
138
+ "tokenizer_class": null,
139
+ "top_k": 50,
140
+ "top_p": 1.0,
141
+ "torch_dtype": null,
142
+ "torchscript": false,
143
+ "transformers_version": "4.10.0.dev0",
144
+ "use_bfloat16": false,
145
+ "vocab_size": 99
146
+ },
147
+ "transformers_version": null,
148
+ "vision_config": {
149
+ "_name_or_path": "",
150
+ "add_cross_attention": false,
151
+ "architectures": null,
152
+ "attention_dropout": 0.1,
153
+ "bad_words_ids": null,
154
+ "bos_token_id": null,
155
+ "chunk_size_feed_forward": 0,
156
+ "decoder_start_token_id": null,
157
+ "diversity_penalty": 0.0,
158
+ "do_sample": false,
159
+ "dropout": 0.1,
160
+ "early_stopping": false,
161
+ "encoder_no_repeat_ngram_size": 0,
162
+ "eos_token_id": null,
163
+ "finetuning_task": null,
164
+ "forced_bos_token_id": null,
165
+ "forced_eos_token_id": null,
166
+ "gradient_checkpointing": false,
167
+ "hidden_act": "quick_gelu",
168
+ "hidden_size": 32,
169
+ "id2label": {
170
+ "0": "LABEL_0",
171
+ "1": "LABEL_1"
172
+ },
173
+ "image_size": 30,
174
+ "initializer_factor": 1.0,
175
+ "initializer_range": 0.02,
176
+ "intermediate_size": 37,
177
+ "is_decoder": false,
178
+ "is_encoder_decoder": false,
179
+ "label2id": {
180
+ "LABEL_0": 0,
181
+ "LABEL_1": 1
182
+ },
183
+ "layer_norm_eps": 1e-05,
184
+ "length_penalty": 1.0,
185
+ "max_length": 20,
186
+ "min_length": 0,
187
+ "model_type": "clip_vision_model",
188
+ "no_repeat_ngram_size": 0,
189
+ "num_attention_heads": 4,
190
+ "num_beam_groups": 1,
191
+ "num_beams": 1,
192
+ "num_channels": 3,
193
+ "num_hidden_layers": 5,
194
+ "num_return_sequences": 1,
195
+ "output_attentions": false,
196
+ "output_hidden_states": false,
197
+ "output_scores": false,
198
+ "pad_token_id": null,
199
+ "patch_size": 2,
200
+ "prefix": null,
201
+ "problem_type": null,
202
+ "pruned_heads": {},
203
+ "remove_invalid_values": false,
204
+ "repetition_penalty": 1.0,
205
+ "return_dict": true,
206
+ "return_dict_in_generate": false,
207
+ "sep_token_id": null,
208
+ "task_specific_params": null,
209
+ "temperature": 1.0,
210
+ "tie_encoder_decoder": false,
211
+ "tie_word_embeddings": true,
212
+ "tokenizer_class": null,
213
+ "top_k": 50,
214
+ "top_p": 1.0,
215
+ "torch_dtype": null,
216
+ "torchscript": false,
217
+ "transformers_version": "4.10.0.dev0",
218
+ "use_bfloat16": false
219
+ },
220
+ "vision_config_dict": {
221
+ "_name_or_path": "",
222
+ "add_cross_attention": false,
223
+ "architectures": null,
224
+ "attention_dropout": 0.1,
225
+ "bad_words_ids": null,
226
+ "bos_token_id": null,
227
+ "chunk_size_feed_forward": 0,
228
+ "decoder_start_token_id": null,
229
+ "diversity_penalty": 0.0,
230
+ "do_sample": false,
231
+ "dropout": 0.1,
232
+ "early_stopping": false,
233
+ "encoder_no_repeat_ngram_size": 0,
234
+ "eos_token_id": null,
235
+ "finetuning_task": null,
236
+ "forced_bos_token_id": null,
237
+ "forced_eos_token_id": null,
238
+ "gradient_checkpointing": false,
239
+ "hidden_act": "quick_gelu",
240
+ "hidden_size": 32,
241
+ "id2label": {
242
+ "0": "LABEL_0",
243
+ "1": "LABEL_1"
244
+ },
245
+ "image_size": 30,
246
+ "initializer_factor": 1.0,
247
+ "initializer_range": 0.02,
248
+ "intermediate_size": 37,
249
+ "is_decoder": false,
250
+ "is_encoder_decoder": false,
251
+ "label2id": {
252
+ "LABEL_0": 0,
253
+ "LABEL_1": 1
254
+ },
255
+ "layer_norm_eps": 1e-05,
256
+ "length_penalty": 1.0,
257
+ "max_length": 20,
258
+ "min_length": 0,
259
+ "model_type": "clip_vision_model",
260
+ "no_repeat_ngram_size": 0,
261
+ "num_attention_heads": 4,
262
+ "num_beam_groups": 1,
263
+ "num_beams": 1,
264
+ "num_channels": 3,
265
+ "num_hidden_layers": 5,
266
+ "num_return_sequences": 1,
267
+ "output_attentions": false,
268
+ "output_hidden_states": false,
269
+ "output_scores": false,
270
+ "pad_token_id": null,
271
+ "patch_size": 2,
272
+ "prefix": null,
273
+ "problem_type": null,
274
+ "pruned_heads": {},
275
+ "remove_invalid_values": false,
276
+ "repetition_penalty": 1.0,
277
+ "return_dict": true,
278
+ "return_dict_in_generate": false,
279
+ "sep_token_id": null,
280
+ "task_specific_params": null,
281
+ "temperature": 1.0,
282
+ "tie_encoder_decoder": false,
283
+ "tie_word_embeddings": true,
284
+ "tokenizer_class": null,
285
+ "top_k": 50,
286
+ "top_p": 1.0,
287
+ "torch_dtype": null,
288
+ "torchscript": false,
289
+ "transformers_version": "4.10.0.dev0",
290
+ "use_bfloat16": false
291
+ }
292
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:257167eba9fc910d22ef63e38e13eca98b2b0a975fa66bc52578a6cff722a06f
3
+ size 458721