Hugging Face's logo

Shubhamai
/
tiny-random-clip-zero-shot-image-classification

Zero-Shot Image Classification
Transformers
JAX
clip
Inference Endpoints
Model card Files Community
Shubhamai commited on
Commit
d366b18
•
1 Parent(s): 0b472c2

Upload model

Browse files
Files changed (2) hide show
  1. config.json +313 -0
  2. flax_model.msgpack +3 -0
config.json ADDED
@@ -0,0 +1,313 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "b965c5deee645e96dcc40a8cdd260a7595b93354",
3
+ "_name_or_path": "hf-internal-testing/tiny-random-clip-zero-shot-image-classification",
4
+ "architectures": [
5
+ "CLIPModel"
6
+ ],
7
+ "initializer_factor": 1.0,
8
+ "logit_scale_init_value": 2.6592,
9
+ "model_type": "clip",
10
+ "projection_dim": 64,
11
+ "text_config": {
12
+ "_name_or_path": "",
13
+ "add_cross_attention": false,
14
+ "architectures": null,
15
+ "attention_dropout": 0.1,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 0,
19
+ "chunk_size_feed_forward": 0,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": null,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "dropout": 0.1,
25
+ "early_stopping": false,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": 2,
28
+ "exponential_decay_length_penalty": null,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": null,
31
+ "forced_eos_token_id": null,
32
+ "gradient_checkpointing": false,
33
+ "hidden_act": "quick_gelu",
34
+ "hidden_size": 32,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1"
38
+ },
39
+ "initializer_factor": 1.0,
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 37,
42
+ "is_decoder": false,
43
+ "is_encoder_decoder": false,
44
+ "label2id": {
45
+ "LABEL_0": 0,
46
+ "LABEL_1": 1
47
+ },
48
+ "layer_norm_eps": 1e-05,
49
+ "length_penalty": 1.0,
50
+ "max_length": 20,
51
+ "max_position_embeddings": 512,
52
+ "min_length": 0,
53
+ "model_type": "clip_text_model",
54
+ "no_repeat_ngram_size": 0,
55
+ "num_attention_heads": 4,
56
+ "num_beam_groups": 1,
57
+ "num_beams": 1,
58
+ "num_hidden_layers": 5,
59
+ "num_return_sequences": 1,
60
+ "output_attentions": false,
61
+ "output_hidden_states": false,
62
+ "output_scores": false,
63
+ "pad_token_id": 1,
64
+ "prefix": null,
65
+ "problem_type": null,
66
+ "projection_dim": 512,
67
+ "pruned_heads": {},
68
+ "remove_invalid_values": false,
69
+ "repetition_penalty": 1.0,
70
+ "return_dict": true,
71
+ "return_dict_in_generate": false,
72
+ "sep_token_id": null,
73
+ "suppress_tokens": null,
74
+ "task_specific_params": null,
75
+ "temperature": 1.0,
76
+ "tf_legacy_loss": false,
77
+ "tie_encoder_decoder": false,
78
+ "tie_word_embeddings": true,
79
+ "tokenizer_class": null,
80
+ "top_k": 50,
81
+ "top_p": 1.0,
82
+ "torch_dtype": null,
83
+ "torchscript": false,
84
+ "transformers_version": "4.27.0.dev0",
85
+ "typical_p": 1.0,
86
+ "use_bfloat16": false,
87
+ "vocab_size": 99
88
+ },
89
+ "text_config_dict": {
90
+ "_name_or_path": "",
91
+ "add_cross_attention": false,
92
+ "architectures": null,
93
+ "attention_dropout": 0.1,
94
+ "bad_words_ids": null,
95
+ "bos_token_id": 0,
96
+ "chunk_size_feed_forward": 0,
97
+ "decoder_start_token_id": null,
98
+ "diversity_penalty": 0.0,
99
+ "do_sample": false,
100
+ "dropout": 0.1,
101
+ "early_stopping": false,
102
+ "encoder_no_repeat_ngram_size": 0,
103
+ "eos_token_id": 2,
104
+ "finetuning_task": null,
105
+ "forced_bos_token_id": null,
106
+ "forced_eos_token_id": null,
107
+ "gradient_checkpointing": false,
108
+ "hidden_act": "quick_gelu",
109
+ "hidden_size": 32,
110
+ "id2label": {
111
+ "0": "LABEL_0",
112
+ "1": "LABEL_1"
113
+ },
114
+ "initializer_factor": 1.0,
115
+ "initializer_range": 0.02,
116
+ "intermediate_size": 37,
117
+ "is_decoder": false,
118
+ "is_encoder_decoder": false,
119
+ "label2id": {
120
+ "LABEL_0": 0,
121
+ "LABEL_1": 1
122
+ },
123
+ "layer_norm_eps": 1e-05,
124
+ "length_penalty": 1.0,
125
+ "max_length": 20,
126
+ "max_position_embeddings": 512,
127
+ "min_length": 0,
128
+ "model_type": "clip_text_model",
129
+ "no_repeat_ngram_size": 0,
130
+ "num_attention_heads": 4,
131
+ "num_beam_groups": 1,
132
+ "num_beams": 1,
133
+ "num_hidden_layers": 5,
134
+ "num_return_sequences": 1,
135
+ "output_attentions": false,
136
+ "output_hidden_states": false,
137
+ "output_scores": false,
138
+ "pad_token_id": 1,
139
+ "prefix": null,
140
+ "problem_type": null,
141
+ "pruned_heads": {},
142
+ "remove_invalid_values": false,
143
+ "repetition_penalty": 1.0,
144
+ "return_dict": true,
145
+ "return_dict_in_generate": false,
146
+ "sep_token_id": null,
147
+ "task_specific_params": null,
148
+ "temperature": 1.0,
149
+ "tie_encoder_decoder": false,
150
+ "tie_word_embeddings": true,
151
+ "tokenizer_class": null,
152
+ "top_k": 50,
153
+ "top_p": 1.0,
154
+ "torch_dtype": null,
155
+ "torchscript": false,
156
+ "transformers_version": "4.11.0.dev0",
157
+ "use_bfloat16": false,
158
+ "vocab_size": 99
159
+ },
160
+ "transformers_version": null,
161
+ "vision_config": {
162
+ "_name_or_path": "",
163
+ "add_cross_attention": false,
164
+ "architectures": null,
165
+ "attention_dropout": 0.1,
166
+ "bad_words_ids": null,
167
+ "begin_suppress_tokens": null,
168
+ "bos_token_id": null,
169
+ "chunk_size_feed_forward": 0,
170
+ "cross_attention_hidden_size": null,
171
+ "decoder_start_token_id": null,
172
+ "diversity_penalty": 0.0,
173
+ "do_sample": false,
174
+ "dropout": 0.1,
175
+ "early_stopping": false,
176
+ "encoder_no_repeat_ngram_size": 0,
177
+ "eos_token_id": null,
178
+ "exponential_decay_length_penalty": null,
179
+ "finetuning_task": null,
180
+ "forced_bos_token_id": null,
181
+ "forced_eos_token_id": null,
182
+ "gradient_checkpointing": false,
183
+ "hidden_act": "quick_gelu",
184
+ "hidden_size": 32,
185
+ "id2label": {
186
+ "0": "LABEL_0",
187
+ "1": "LABEL_1"
188
+ },
189
+ "image_size": 30,
190
+ "initializer_factor": 1.0,
191
+ "initializer_range": 0.02,
192
+ "intermediate_size": 37,
193
+ "is_decoder": false,
194
+ "is_encoder_decoder": false,
195
+ "label2id": {
196
+ "LABEL_0": 0,
197
+ "LABEL_1": 1
198
+ },
199
+ "layer_norm_eps": 1e-05,
200
+ "length_penalty": 1.0,
201
+ "max_length": 20,
202
+ "min_length": 0,
203
+ "model_type": "clip_vision_model",
204
+ "no_repeat_ngram_size": 0,
205
+ "num_attention_heads": 4,
206
+ "num_beam_groups": 1,
207
+ "num_beams": 1,
208
+ "num_channels": 3,
209
+ "num_hidden_layers": 5,
210
+ "num_return_sequences": 1,
211
+ "output_attentions": false,
212
+ "output_hidden_states": false,
213
+ "output_scores": false,
214
+ "pad_token_id": null,
215
+ "patch_size": 2,
216
+ "prefix": null,
217
+ "problem_type": null,
218
+ "projection_dim": 512,
219
+ "pruned_heads": {},
220
+ "remove_invalid_values": false,
221
+ "repetition_penalty": 1.0,
222
+ "return_dict": true,
223
+ "return_dict_in_generate": false,
224
+ "sep_token_id": null,
225
+ "suppress_tokens": null,
226
+ "task_specific_params": null,
227
+ "temperature": 1.0,
228
+ "tf_legacy_loss": false,
229
+ "tie_encoder_decoder": false,
230
+ "tie_word_embeddings": true,
231
+ "tokenizer_class": null,
232
+ "top_k": 50,
233
+ "top_p": 1.0,
234
+ "torch_dtype": null,
235
+ "torchscript": false,
236
+ "transformers_version": "4.27.0.dev0",
237
+ "typical_p": 1.0,
238
+ "use_bfloat16": false
239
+ },
240
+ "vision_config_dict": {
241
+ "_name_or_path": "",
242
+ "add_cross_attention": false,
243
+ "architectures": null,
244
+ "attention_dropout": 0.1,
245
+ "bad_words_ids": null,
246
+ "bos_token_id": null,
247
+ "chunk_size_feed_forward": 0,
248
+ "decoder_start_token_id": null,
249
+ "diversity_penalty": 0.0,
250
+ "do_sample": false,
251
+ "dropout": 0.1,
252
+ "early_stopping": false,
253
+ "encoder_no_repeat_ngram_size": 0,
254
+ "eos_token_id": null,
255
+ "finetuning_task": null,
256
+ "forced_bos_token_id": null,
257
+ "forced_eos_token_id": null,
258
+ "gradient_checkpointing": false,
259
+ "hidden_act": "quick_gelu",
260
+ "hidden_size": 32,
261
+ "id2label": {
262
+ "0": "LABEL_0",
263
+ "1": "LABEL_1"
264
+ },
265
+ "image_size": 30,
266
+ "initializer_factor": 1.0,
267
+ "initializer_range": 0.02,
268
+ "intermediate_size": 37,
269
+ "is_decoder": false,
270
+ "is_encoder_decoder": false,
271
+ "label2id": {
272
+ "LABEL_0": 0,
273
+ "LABEL_1": 1
274
+ },
275
+ "layer_norm_eps": 1e-05,
276
+ "length_penalty": 1.0,
277
+ "max_length": 20,
278
+ "min_length": 0,
279
+ "model_type": "clip_vision_model",
280
+ "no_repeat_ngram_size": 0,
281
+ "num_attention_heads": 4,
282
+ "num_beam_groups": 1,
283
+ "num_beams": 1,
284
+ "num_channels": 3,
285
+ "num_hidden_layers": 5,
286
+ "num_return_sequences": 1,
287
+ "output_attentions": false,
288
+ "output_hidden_states": false,
289
+ "output_scores": false,
290
+ "pad_token_id": null,
291
+ "patch_size": 2,
292
+ "prefix": null,
293
+ "problem_type": null,
294
+ "pruned_heads": {},
295
+ "remove_invalid_values": false,
296
+ "repetition_penalty": 1.0,
297
+ "return_dict": true,
298
+ "return_dict_in_generate": false,
299
+ "sep_token_id": null,
300
+ "task_specific_params": null,
301
+ "temperature": 1.0,
302
+ "tie_encoder_decoder": false,
303
+ "tie_word_embeddings": true,
304
+ "tokenizer_class": null,
305
+ "top_k": 50,
306
+ "top_p": 1.0,
307
+ "torch_dtype": null,
308
+ "torchscript": false,
309
+ "transformers_version": "4.11.0.dev0",
310
+ "use_bfloat16": false
311
+ },
312
+ "vocab_size": 1000
313
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb9f86d8ed768064b9ab0cb787d37069b4a07aba1be67489152d647ff6b0b5b8
3
+ size 402690