Hugging Face's logo

microsoft
/
xclip-base-patch16-zero-shot

Video Classification
Transformers
PyTorch
Safetensors
English
xclip
feature-extraction
vision
Eval Results
Inference Endpoints
Model card Files Community
2
nielsr HF staff commited on
Commit
9e0144e
•
1 Parent(s): 26761c4

Upload model

Browse files
Files changed (2) hide show
  1. config.json +328 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "XCLIPModel"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "xclip",
9
+ "projection_dim": 512,
10
+ "prompt_alpha": 0.1,
11
+ "prompt_attention_dropout": 0.0,
12
+ "prompt_hidden_act": "quick_gelu",
13
+ "prompt_layers": 2,
14
+ "prompt_num_attention_heads": 8,
15
+ "prompt_projection_dropout": 0.0,
16
+ "text_config": {
17
+ "_name_or_path": "",
18
+ "add_cross_attention": false,
19
+ "architectures": null,
20
+ "attention_dropout": 0.0,
21
+ "bad_words_ids": null,
22
+ "bos_token_id": 0,
23
+ "chunk_size_feed_forward": 0,
24
+ "cross_attention_hidden_size": null,
25
+ "decoder_start_token_id": null,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "dropout": 0.0,
29
+ "early_stopping": false,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "eos_token_id": 2,
32
+ "exponential_decay_length_penalty": null,
33
+ "finetuning_task": null,
34
+ "forced_bos_token_id": null,
35
+ "forced_eos_token_id": null,
36
+ "hidden_act": "quick_gelu",
37
+ "hidden_size": 512,
38
+ "id2label": {
39
+ "0": "LABEL_0",
40
+ "1": "LABEL_1"
41
+ },
42
+ "initializer_factor": 1.0,
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 2048,
45
+ "is_decoder": false,
46
+ "is_encoder_decoder": false,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1
50
+ },
51
+ "layer_norm_eps": 1e-05,
52
+ "length_penalty": 1.0,
53
+ "max_length": 20,
54
+ "max_position_embeddings": 77,
55
+ "min_length": 0,
56
+ "model_type": "xclip_text_model",
57
+ "no_repeat_ngram_size": 0,
58
+ "num_attention_heads": 8,
59
+ "num_beam_groups": 1,
60
+ "num_beams": 1,
61
+ "num_hidden_layers": 12,
62
+ "num_return_sequences": 1,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": 1,
67
+ "prefix": null,
68
+ "problem_type": null,
69
+ "pruned_heads": {},
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "return_dict": true,
73
+ "return_dict_in_generate": false,
74
+ "sep_token_id": null,
75
+ "task_specific_params": null,
76
+ "temperature": 1.0,
77
+ "tf_legacy_loss": false,
78
+ "tie_encoder_decoder": false,
79
+ "tie_word_embeddings": true,
80
+ "tokenizer_class": null,
81
+ "top_k": 50,
82
+ "top_p": 1.0,
83
+ "torch_dtype": null,
84
+ "torchscript": false,
85
+ "transformers_version": "4.22.0.dev0",
86
+ "typical_p": 1.0,
87
+ "use_bfloat16": false,
88
+ "vocab_size": 49408
89
+ },
90
+ "text_config_dict": {
91
+ "_name_or_path": "",
92
+ "add_cross_attention": false,
93
+ "architectures": null,
94
+ "attention_dropout": 0.0,
95
+ "bad_words_ids": null,
96
+ "bos_token_id": 0,
97
+ "chunk_size_feed_forward": 0,
98
+ "cross_attention_hidden_size": null,
99
+ "decoder_start_token_id": null,
100
+ "diversity_penalty": 0.0,
101
+ "do_sample": false,
102
+ "dropout": 0.0,
103
+ "early_stopping": false,
104
+ "encoder_no_repeat_ngram_size": 0,
105
+ "eos_token_id": 2,
106
+ "exponential_decay_length_penalty": null,
107
+ "finetuning_task": null,
108
+ "forced_bos_token_id": null,
109
+ "forced_eos_token_id": null,
110
+ "hidden_act": "quick_gelu",
111
+ "hidden_size": 512,
112
+ "id2label": {
113
+ "0": "LABEL_0",
114
+ "1": "LABEL_1"
115
+ },
116
+ "initializer_factor": 1.0,
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 2048,
119
+ "is_decoder": false,
120
+ "is_encoder_decoder": false,
121
+ "label2id": {
122
+ "LABEL_0": 0,
123
+ "LABEL_1": 1
124
+ },
125
+ "layer_norm_eps": 1e-05,
126
+ "length_penalty": 1.0,
127
+ "max_length": 20,
128
+ "max_position_embeddings": 77,
129
+ "min_length": 0,
130
+ "model_type": "xclip_text_model",
131
+ "no_repeat_ngram_size": 0,
132
+ "num_attention_heads": 8,
133
+ "num_beam_groups": 1,
134
+ "num_beams": 1,
135
+ "num_hidden_layers": 12,
136
+ "num_return_sequences": 1,
137
+ "output_attentions": false,
138
+ "output_hidden_states": false,
139
+ "output_scores": false,
140
+ "pad_token_id": 1,
141
+ "prefix": null,
142
+ "problem_type": null,
143
+ "pruned_heads": {},
144
+ "remove_invalid_values": false,
145
+ "repetition_penalty": 1.0,
146
+ "return_dict": true,
147
+ "return_dict_in_generate": false,
148
+ "sep_token_id": null,
149
+ "task_specific_params": null,
150
+ "temperature": 1.0,
151
+ "tf_legacy_loss": false,
152
+ "tie_encoder_decoder": false,
153
+ "tie_word_embeddings": true,
154
+ "tokenizer_class": null,
155
+ "top_k": 50,
156
+ "top_p": 1.0,
157
+ "torch_dtype": null,
158
+ "torchscript": false,
159
+ "transformers_version": "4.22.0.dev0",
160
+ "typical_p": 1.0,
161
+ "use_bfloat16": false,
162
+ "vocab_size": 49408
163
+ },
164
+ "torch_dtype": "float32",
165
+ "transformers_version": null,
166
+ "vision_config": {
167
+ "_name_or_path": "",
168
+ "add_cross_attention": false,
169
+ "architectures": null,
170
+ "attention_dropout": 0.0,
171
+ "bad_words_ids": null,
172
+ "bos_token_id": null,
173
+ "chunk_size_feed_forward": 0,
174
+ "cross_attention_hidden_size": null,
175
+ "decoder_start_token_id": null,
176
+ "diversity_penalty": 0.0,
177
+ "do_sample": false,
178
+ "drop_path_rate": 0.0,
179
+ "dropout": 0.0,
180
+ "early_stopping": false,
181
+ "encoder_no_repeat_ngram_size": 0,
182
+ "eos_token_id": null,
183
+ "exponential_decay_length_penalty": null,
184
+ "finetuning_task": null,
185
+ "forced_bos_token_id": null,
186
+ "forced_eos_token_id": null,
187
+ "hidden_act": "quick_gelu",
188
+ "hidden_size": 768,
189
+ "id2label": {
190
+ "0": "LABEL_0",
191
+ "1": "LABEL_1"
192
+ },
193
+ "image_size": 224,
194
+ "initializer_factor": 1.0,
195
+ "initializer_range": 0.02,
196
+ "intermediate_size": 3072,
197
+ "is_decoder": false,
198
+ "is_encoder_decoder": false,
199
+ "label2id": {
200
+ "LABEL_0": 0,
201
+ "LABEL_1": 1
202
+ },
203
+ "layer_norm_eps": 1e-05,
204
+ "length_penalty": 1.0,
205
+ "max_length": 20,
206
+ "min_length": 0,
207
+ "mit_hidden_size": 512,
208
+ "mit_intermediate_size": 2048,
209
+ "mit_num_attention_heads": 8,
210
+ "mit_num_hidden_layers": 1,
211
+ "model_type": "xclip_vision_model",
212
+ "no_repeat_ngram_size": 0,
213
+ "num_attention_heads": 12,
214
+ "num_beam_groups": 1,
215
+ "num_beams": 1,
216
+ "num_channels": 3,
217
+ "num_frames": 32,
218
+ "num_hidden_layers": 12,
219
+ "num_return_sequences": 1,
220
+ "output_attentions": false,
221
+ "output_hidden_states": false,
222
+ "output_scores": false,
223
+ "pad_token_id": null,
224
+ "patch_size": 16,
225
+ "prefix": null,
226
+ "problem_type": null,
227
+ "pruned_heads": {},
228
+ "remove_invalid_values": false,
229
+ "repetition_penalty": 1.0,
230
+ "return_dict": true,
231
+ "return_dict_in_generate": false,
232
+ "sep_token_id": null,
233
+ "task_specific_params": null,
234
+ "temperature": 1.0,
235
+ "tf_legacy_loss": false,
236
+ "tie_encoder_decoder": false,
237
+ "tie_word_embeddings": true,
238
+ "tokenizer_class": null,
239
+ "top_k": 50,
240
+ "top_p": 1.0,
241
+ "torch_dtype": null,
242
+ "torchscript": false,
243
+ "transformers_version": "4.22.0.dev0",
244
+ "typical_p": 1.0,
245
+ "use_bfloat16": false
246
+ },
247
+ "vision_config_dict": {
248
+ "_name_or_path": "",
249
+ "add_cross_attention": false,
250
+ "architectures": null,
251
+ "attention_dropout": 0.0,
252
+ "bad_words_ids": null,
253
+ "bos_token_id": null,
254
+ "chunk_size_feed_forward": 0,
255
+ "cross_attention_hidden_size": null,
256
+ "decoder_start_token_id": null,
257
+ "diversity_penalty": 0.0,
258
+ "do_sample": false,
259
+ "drop_path_rate": 0.0,
260
+ "dropout": 0.0,
261
+ "early_stopping": false,
262
+ "encoder_no_repeat_ngram_size": 0,
263
+ "eos_token_id": null,
264
+ "exponential_decay_length_penalty": null,
265
+ "finetuning_task": null,
266
+ "forced_bos_token_id": null,
267
+ "forced_eos_token_id": null,
268
+ "hidden_act": "quick_gelu",
269
+ "hidden_size": 768,
270
+ "id2label": {
271
+ "0": "LABEL_0",
272
+ "1": "LABEL_1"
273
+ },
274
+ "image_size": 224,
275
+ "initializer_factor": 1.0,
276
+ "initializer_range": 0.02,
277
+ "intermediate_size": 3072,
278
+ "is_decoder": false,
279
+ "is_encoder_decoder": false,
280
+ "label2id": {
281
+ "LABEL_0": 0,
282
+ "LABEL_1": 1
283
+ },
284
+ "layer_norm_eps": 1e-05,
285
+ "length_penalty": 1.0,
286
+ "max_length": 20,
287
+ "min_length": 0,
288
+ "mit_hidden_size": 512,
289
+ "mit_intermediate_size": 2048,
290
+ "mit_num_attention_heads": 8,
291
+ "mit_num_hidden_layers": 1,
292
+ "model_type": "xclip_vision_model",
293
+ "no_repeat_ngram_size": 0,
294
+ "num_attention_heads": 12,
295
+ "num_beam_groups": 1,
296
+ "num_beams": 1,
297
+ "num_channels": 3,
298
+ "num_frames": 32,
299
+ "num_hidden_layers": 12,
300
+ "num_return_sequences": 1,
301
+ "output_attentions": false,
302
+ "output_hidden_states": false,
303
+ "output_scores": false,
304
+ "pad_token_id": null,
305
+ "patch_size": 16,
306
+ "prefix": null,
307
+ "problem_type": null,
308
+ "pruned_heads": {},
309
+ "remove_invalid_values": false,
310
+ "repetition_penalty": 1.0,
311
+ "return_dict": true,
312
+ "return_dict_in_generate": false,
313
+ "sep_token_id": null,
314
+ "task_specific_params": null,
315
+ "temperature": 1.0,
316
+ "tf_legacy_loss": false,
317
+ "tie_encoder_decoder": false,
318
+ "tie_word_embeddings": true,
319
+ "tokenizer_class": null,
320
+ "top_k": 50,
321
+ "top_p": 1.0,
322
+ "torch_dtype": null,
323
+ "torchscript": false,
324
+ "transformers_version": "4.22.0.dev0",
325
+ "typical_p": 1.0,
326
+ "use_bfloat16": false
327
+ }
328
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f57805daf0db792cc4a09e99b72c97feb2b7e7a0a99c219718d28186d852fe4
3
+ size 779959711