theodor1289 commited on
Commit
b509df1
1 Parent(s): 38cab12

Upload FlavaForPreTraining

Browse files
Files changed (2) hide show
  1. config.json +330 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "FlavaForPreTraining"
5
+ ],
6
+ "ce_ignore_index": -100,
7
+ "compile_submodels": true,
8
+ "global_backprop_contrastive": true,
9
+ "global_contrastive_weight": 1.0,
10
+ "hidden_size": 516,
11
+ "image_codebook_config": {
12
+ "_name_or_path": "",
13
+ "add_cross_attention": false,
14
+ "architectures": null,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": null,
18
+ "chunk_size_feed_forward": 0,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": null,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "freeze": true,
31
+ "hidden_size": 256,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "input_channels": 3,
38
+ "is_decoder": false,
39
+ "is_encoder_decoder": false,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1
43
+ },
44
+ "length_penalty": 1.0,
45
+ "max_length": 20,
46
+ "min_length": 0,
47
+ "model_type": "flava_image_codebook",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_beam_groups": 1,
50
+ "num_beams": 1,
51
+ "num_blocks_per_group": 2,
52
+ "num_groups": 4,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": null,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "repetition_penalty": 1.0,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "sep_token_id": null,
66
+ "suppress_tokens": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tf_legacy_loss": false,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": true,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": null,
76
+ "torchscript": false,
77
+ "transformers_version": "4.29.2",
78
+ "typical_p": 1.0,
79
+ "use_bfloat16": false,
80
+ "vocab_size": 8192
81
+ },
82
+ "image_config": {
83
+ "_name_or_path": "",
84
+ "add_cross_attention": false,
85
+ "architectures": null,
86
+ "attention_probs_dropout_prob": 0.0,
87
+ "bad_words_ids": null,
88
+ "begin_suppress_tokens": null,
89
+ "bos_token_id": null,
90
+ "chunk_size_feed_forward": 0,
91
+ "cross_attention_hidden_size": null,
92
+ "decoder_start_token_id": null,
93
+ "diversity_penalty": 0.0,
94
+ "do_sample": false,
95
+ "early_stopping": false,
96
+ "encoder_no_repeat_ngram_size": 0,
97
+ "eos_token_id": null,
98
+ "exponential_decay_length_penalty": null,
99
+ "finetuning_task": null,
100
+ "forced_bos_token_id": null,
101
+ "forced_eos_token_id": null,
102
+ "hidden_act": "gelu",
103
+ "hidden_dropout_prob": 0.0,
104
+ "hidden_size": 516,
105
+ "id2label": {
106
+ "0": "LABEL_0",
107
+ "1": "LABEL_1"
108
+ },
109
+ "image_size": 224,
110
+ "initializer_range": 0.02,
111
+ "intermediate_size": 3072,
112
+ "is_decoder": false,
113
+ "is_encoder_decoder": false,
114
+ "label2id": {
115
+ "LABEL_0": 0,
116
+ "LABEL_1": 1
117
+ },
118
+ "layer_norm_eps": 1e-12,
119
+ "length_penalty": 1.0,
120
+ "mask_token": true,
121
+ "max_length": 20,
122
+ "min_length": 0,
123
+ "model_type": "flava_image_model",
124
+ "no_repeat_ngram_size": 0,
125
+ "num_attention_heads": 12,
126
+ "num_beam_groups": 1,
127
+ "num_beams": 1,
128
+ "num_channels": 3,
129
+ "num_hidden_layers": 6,
130
+ "num_return_sequences": 1,
131
+ "output_attentions": false,
132
+ "output_hidden_states": false,
133
+ "output_scores": false,
134
+ "pad_token_id": null,
135
+ "patch_size": 16,
136
+ "prefix": null,
137
+ "problem_type": null,
138
+ "pruned_heads": {},
139
+ "qkv_bias": true,
140
+ "remove_invalid_values": false,
141
+ "repetition_penalty": 1.0,
142
+ "return_dict": true,
143
+ "return_dict_in_generate": false,
144
+ "sep_token_id": null,
145
+ "suppress_tokens": null,
146
+ "task_specific_params": null,
147
+ "temperature": 1.0,
148
+ "tf_legacy_loss": false,
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": "4.29.2",
157
+ "typical_p": 1.0,
158
+ "use_bfloat16": false,
159
+ "vocab_size": 8192
160
+ },
161
+ "init_codebook": true,
162
+ "initializer_factor": 1.0,
163
+ "initializer_range": 0.02,
164
+ "itm_weight": 1.0,
165
+ "layer_norm_eps": 1e-12,
166
+ "logit_scale_init_value": 2.6592,
167
+ "mim_weight": 1.0,
168
+ "mlm_weight": 1.0,
169
+ "mmm_image_weight": 1.0,
170
+ "mmm_text_weight": 1.0,
171
+ "model_type": "flava",
172
+ "multimodal_config": {
173
+ "_name_or_path": "",
174
+ "add_cross_attention": false,
175
+ "architectures": null,
176
+ "attention_probs_dropout_prob": 0.0,
177
+ "bad_words_ids": null,
178
+ "begin_suppress_tokens": null,
179
+ "bos_token_id": null,
180
+ "chunk_size_feed_forward": 0,
181
+ "cross_attention_hidden_size": null,
182
+ "decoder_start_token_id": null,
183
+ "diversity_penalty": 0.0,
184
+ "do_sample": false,
185
+ "early_stopping": false,
186
+ "encoder_no_repeat_ngram_size": 0,
187
+ "eos_token_id": null,
188
+ "exponential_decay_length_penalty": null,
189
+ "finetuning_task": null,
190
+ "forced_bos_token_id": null,
191
+ "forced_eos_token_id": null,
192
+ "hidden_act": "gelu",
193
+ "hidden_dropout_prob": 0.0,
194
+ "hidden_size": 516,
195
+ "id2label": {
196
+ "0": "LABEL_0",
197
+ "1": "LABEL_1"
198
+ },
199
+ "initializer_range": 0.02,
200
+ "intermediate_size": 3072,
201
+ "is_decoder": false,
202
+ "is_encoder_decoder": false,
203
+ "label2id": {
204
+ "LABEL_0": 0,
205
+ "LABEL_1": 1
206
+ },
207
+ "layer_norm_eps": 1e-12,
208
+ "length_penalty": 1.0,
209
+ "max_length": 20,
210
+ "min_length": 0,
211
+ "model_type": "flava_multimodal_model",
212
+ "no_repeat_ngram_size": 0,
213
+ "num_attention_heads": 12,
214
+ "num_beam_groups": 1,
215
+ "num_beams": 1,
216
+ "num_hidden_layers": 6,
217
+ "num_return_sequences": 1,
218
+ "output_attentions": false,
219
+ "output_hidden_states": false,
220
+ "output_scores": false,
221
+ "pad_token_id": null,
222
+ "prefix": null,
223
+ "problem_type": null,
224
+ "pruned_heads": {},
225
+ "qkv_bias": true,
226
+ "remove_invalid_values": false,
227
+ "repetition_penalty": 1.0,
228
+ "return_dict": true,
229
+ "return_dict_in_generate": false,
230
+ "sep_token_id": null,
231
+ "suppress_tokens": null,
232
+ "task_specific_params": null,
233
+ "temperature": 1.0,
234
+ "tf_legacy_loss": false,
235
+ "tie_encoder_decoder": false,
236
+ "tie_word_embeddings": true,
237
+ "tokenizer_class": null,
238
+ "top_k": 50,
239
+ "top_p": 1.0,
240
+ "torch_dtype": null,
241
+ "torchscript": false,
242
+ "transformers_version": "4.29.2",
243
+ "typical_p": 1.0,
244
+ "use_bfloat16": false,
245
+ "use_cls_token": true
246
+ },
247
+ "projection_dim": 516,
248
+ "return_loss": true,
249
+ "skip_unmasked_multimodal_encoder": true,
250
+ "text_config": {
251
+ "_name_or_path": "",
252
+ "add_cross_attention": false,
253
+ "architectures": null,
254
+ "attention_probs_dropout_prob": 0.0,
255
+ "bad_words_ids": null,
256
+ "begin_suppress_tokens": null,
257
+ "bos_token_id": null,
258
+ "chunk_size_feed_forward": 0,
259
+ "cross_attention_hidden_size": null,
260
+ "decoder_start_token_id": null,
261
+ "diversity_penalty": 0.0,
262
+ "do_sample": false,
263
+ "early_stopping": false,
264
+ "encoder_no_repeat_ngram_size": 0,
265
+ "eos_token_id": null,
266
+ "exponential_decay_length_penalty": null,
267
+ "finetuning_task": null,
268
+ "forced_bos_token_id": null,
269
+ "forced_eos_token_id": null,
270
+ "hidden_act": "gelu",
271
+ "hidden_dropout_prob": 0.0,
272
+ "hidden_size": 516,
273
+ "id2label": {
274
+ "0": "LABEL_0",
275
+ "1": "LABEL_1"
276
+ },
277
+ "initializer_range": 0.02,
278
+ "intermediate_size": 3072,
279
+ "is_decoder": false,
280
+ "is_encoder_decoder": false,
281
+ "label2id": {
282
+ "LABEL_0": 0,
283
+ "LABEL_1": 1
284
+ },
285
+ "layer_norm_eps": 1e-12,
286
+ "length_penalty": 1.0,
287
+ "max_length": 20,
288
+ "max_position_embeddings": 512,
289
+ "min_length": 0,
290
+ "model_type": "flava_text_model",
291
+ "no_repeat_ngram_size": 0,
292
+ "num_attention_heads": 12,
293
+ "num_beam_groups": 1,
294
+ "num_beams": 1,
295
+ "num_hidden_layers": 6,
296
+ "num_return_sequences": 1,
297
+ "output_attentions": false,
298
+ "output_hidden_states": false,
299
+ "output_scores": false,
300
+ "pad_token_id": 0,
301
+ "position_embedding_type": "absolute",
302
+ "prefix": null,
303
+ "problem_type": null,
304
+ "pruned_heads": {},
305
+ "qkv_bias": true,
306
+ "remove_invalid_values": false,
307
+ "repetition_penalty": 1.0,
308
+ "return_dict": true,
309
+ "return_dict_in_generate": false,
310
+ "sep_token_id": null,
311
+ "suppress_tokens": null,
312
+ "task_specific_params": null,
313
+ "temperature": 1.0,
314
+ "tf_legacy_loss": false,
315
+ "tie_encoder_decoder": false,
316
+ "tie_word_embeddings": true,
317
+ "tokenizer_class": null,
318
+ "top_k": 50,
319
+ "top_p": 1.0,
320
+ "torch_dtype": null,
321
+ "torchscript": false,
322
+ "transformers_version": "4.29.2",
323
+ "type_vocab_size": 2,
324
+ "typical_p": 1.0,
325
+ "use_bfloat16": false,
326
+ "vocab_size": 30522
327
+ },
328
+ "torch_dtype": "float32",
329
+ "transformers_version": null
330
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25d4226fd8d36d919c1e00c33ceb9f5715890a06f7e1c889cb1f1ca8f0451721
3
+ size 759820969