main-horse commited on
Commit
e2480e7
1 Parent(s): b4846f1

Upload Blip2ForConditionalGeneration

Browse files
config.json ADDED
@@ -0,0 +1,285 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "Blip2ForConditionalGeneration"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "initializer_range": 0.02,
8
+ "is_encoder_decoder": true,
9
+ "model_type": "blip-2",
10
+ "num_query_tokens": 32,
11
+ "qformer_config": {
12
+ "_name_or_path": "",
13
+ "add_cross_attention": false,
14
+ "architectures": null,
15
+ "attention_probs_dropout_prob": 0.1,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": null,
19
+ "chunk_size_feed_forward": 0,
20
+ "classifier_dropout": null,
21
+ "cross_attention_frequency": 2,
22
+ "cross_attention_hidden_size": null,
23
+ "decoder_start_token_id": null,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "early_stopping": false,
27
+ "encoder_hidden_size": 1408,
28
+ "encoder_no_repeat_ngram_size": 0,
29
+ "eos_token_id": null,
30
+ "exponential_decay_length_penalty": null,
31
+ "finetuning_task": null,
32
+ "forced_bos_token_id": null,
33
+ "forced_eos_token_id": null,
34
+ "hidden_act": "gelu",
35
+ "hidden_dropout_prob": 0.1,
36
+ "hidden_size": 768,
37
+ "id2label": {
38
+ "0": "LABEL_0",
39
+ "1": "LABEL_1"
40
+ },
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 3072,
43
+ "is_decoder": false,
44
+ "is_encoder_decoder": false,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1
48
+ },
49
+ "layer_norm_eps": 1e-12,
50
+ "length_penalty": 1.0,
51
+ "max_length": 20,
52
+ "max_position_embeddings": 512,
53
+ "min_length": 0,
54
+ "model_type": "blip_2_qformer",
55
+ "no_repeat_ngram_size": 0,
56
+ "num_attention_heads": 12,
57
+ "num_beam_groups": 1,
58
+ "num_beams": 1,
59
+ "num_hidden_layers": 12,
60
+ "num_return_sequences": 1,
61
+ "output_attentions": false,
62
+ "output_hidden_states": false,
63
+ "output_scores": false,
64
+ "pad_token_id": 0,
65
+ "position_embedding_type": "absolute",
66
+ "prefix": null,
67
+ "problem_type": null,
68
+ "pruned_heads": {},
69
+ "remove_invalid_values": false,
70
+ "repetition_penalty": 1.0,
71
+ "return_dict": true,
72
+ "return_dict_in_generate": false,
73
+ "sep_token_id": null,
74
+ "suppress_tokens": 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": "4.27.4",
86
+ "typical_p": 1.0,
87
+ "use_bfloat16": false,
88
+ "vocab_size": 30522
89
+ },
90
+ "text_config": {
91
+ "_name_or_path": "",
92
+ "add_cross_attention": false,
93
+ "architectures": [
94
+ "T5ForConditionalGeneration"
95
+ ],
96
+ "bad_words_ids": null,
97
+ "begin_suppress_tokens": null,
98
+ "bos_token_id": 1,
99
+ "chunk_size_feed_forward": 0,
100
+ "cross_attention_hidden_size": null,
101
+ "d_ff": 5120,
102
+ "d_kv": 64,
103
+ "d_model": 2048,
104
+ "decoder_start_token_id": 0,
105
+ "dense_act_fn": "gelu",
106
+ "diversity_penalty": 0.0,
107
+ "do_sample": false,
108
+ "dropout_rate": 0.1,
109
+ "early_stopping": false,
110
+ "encoder_no_repeat_ngram_size": 0,
111
+ "eos_token_id": 1,
112
+ "exponential_decay_length_penalty": null,
113
+ "feed_forward_proj": "gated-gelu",
114
+ "finetuning_task": null,
115
+ "forced_bos_token_id": null,
116
+ "forced_eos_token_id": null,
117
+ "id2label": {
118
+ "0": "LABEL_0",
119
+ "1": "LABEL_1"
120
+ },
121
+ "initializer_factor": 1.0,
122
+ "is_decoder": false,
123
+ "is_encoder_decoder": true,
124
+ "is_gated_act": true,
125
+ "label2id": {
126
+ "LABEL_0": 0,
127
+ "LABEL_1": 1
128
+ },
129
+ "layer_norm_epsilon": 1e-06,
130
+ "length_penalty": 1.0,
131
+ "max_length": 20,
132
+ "min_length": 0,
133
+ "model_type": "t5",
134
+ "n_positions": 512,
135
+ "no_repeat_ngram_size": 0,
136
+ "num_beam_groups": 1,
137
+ "num_beams": 1,
138
+ "num_decoder_layers": 24,
139
+ "num_heads": 32,
140
+ "num_layers": 24,
141
+ "num_return_sequences": 1,
142
+ "output_attentions": false,
143
+ "output_hidden_states": false,
144
+ "output_past": true,
145
+ "output_scores": false,
146
+ "pad_token_id": 0,
147
+ "prefix": null,
148
+ "problem_type": null,
149
+ "pruned_heads": {},
150
+ "relative_attention_max_distance": 128,
151
+ "relative_attention_num_buckets": 32,
152
+ "remove_invalid_values": false,
153
+ "repetition_penalty": 1.0,
154
+ "return_dict": true,
155
+ "return_dict_in_generate": false,
156
+ "sep_token_id": null,
157
+ "suppress_tokens": null,
158
+ "task_specific_params": {
159
+ "summarization": {
160
+ "early_stopping": true,
161
+ "length_penalty": 2.0,
162
+ "max_length": 200,
163
+ "min_length": 30,
164
+ "no_repeat_ngram_size": 3,
165
+ "num_beams": 4,
166
+ "prefix": "summarize: "
167
+ },
168
+ "translation_en_to_de": {
169
+ "early_stopping": true,
170
+ "max_length": 300,
171
+ "num_beams": 4,
172
+ "prefix": "translate English to German: "
173
+ },
174
+ "translation_en_to_fr": {
175
+ "early_stopping": true,
176
+ "max_length": 300,
177
+ "num_beams": 4,
178
+ "prefix": "translate English to French: "
179
+ },
180
+ "translation_en_to_ro": {
181
+ "early_stopping": true,
182
+ "max_length": 300,
183
+ "num_beams": 4,
184
+ "prefix": "translate English to Romanian: "
185
+ }
186
+ },
187
+ "temperature": 1.0,
188
+ "tf_legacy_loss": false,
189
+ "tie_encoder_decoder": false,
190
+ "tie_word_embeddings": false,
191
+ "tokenizer_class": null,
192
+ "top_k": 50,
193
+ "top_p": 1.0,
194
+ "torch_dtype": "float32",
195
+ "torchscript": false,
196
+ "transformers_version": "4.27.4",
197
+ "typical_p": 1.0,
198
+ "use_bfloat16": false,
199
+ "use_cache": true,
200
+ "vocab_size": 32128
201
+ },
202
+ "tie_word_embeddings": false,
203
+ "torch_dtype": "float32",
204
+ "transformers_version": null,
205
+ "use_decoder_only_language_model": false,
206
+ "vision_config": {
207
+ "_name_or_path": "",
208
+ "add_cross_attention": false,
209
+ "architectures": null,
210
+ "attention_dropout": 0.0,
211
+ "bad_words_ids": null,
212
+ "begin_suppress_tokens": null,
213
+ "bos_token_id": null,
214
+ "chunk_size_feed_forward": 0,
215
+ "cross_attention_hidden_size": null,
216
+ "decoder_start_token_id": null,
217
+ "diversity_penalty": 0.0,
218
+ "do_sample": false,
219
+ "dropout": 0.0,
220
+ "early_stopping": false,
221
+ "encoder_no_repeat_ngram_size": 0,
222
+ "eos_token_id": null,
223
+ "exponential_decay_length_penalty": null,
224
+ "finetuning_task": null,
225
+ "forced_bos_token_id": null,
226
+ "forced_eos_token_id": null,
227
+ "hidden_act": "gelu",
228
+ "hidden_size": 1408,
229
+ "id2label": {
230
+ "0": "LABEL_0",
231
+ "1": "LABEL_1"
232
+ },
233
+ "image_size": 364,
234
+ "initializer_factor": 1.0,
235
+ "initializer_range": 1e-10,
236
+ "intermediate_size": 6144,
237
+ "is_decoder": false,
238
+ "is_encoder_decoder": false,
239
+ "label2id": {
240
+ "LABEL_0": 0,
241
+ "LABEL_1": 1
242
+ },
243
+ "layer_norm_eps": 1e-05,
244
+ "length_penalty": 1.0,
245
+ "max_length": 20,
246
+ "min_length": 0,
247
+ "model_type": "blip_2_vision_model",
248
+ "no_repeat_ngram_size": 0,
249
+ "num_attention_heads": 16,
250
+ "num_beam_groups": 1,
251
+ "num_beams": 1,
252
+ "num_channels": 3,
253
+ "num_hidden_layers": 39,
254
+ "num_return_sequences": 1,
255
+ "output_attentions": false,
256
+ "output_hidden_states": false,
257
+ "output_scores": false,
258
+ "pad_token_id": null,
259
+ "patch_size": 14,
260
+ "prefix": null,
261
+ "problem_type": null,
262
+ "projection_dim": 512,
263
+ "pruned_heads": {},
264
+ "qkv_bias": true,
265
+ "remove_invalid_values": false,
266
+ "repetition_penalty": 1.0,
267
+ "return_dict": true,
268
+ "return_dict_in_generate": false,
269
+ "sep_token_id": null,
270
+ "suppress_tokens": null,
271
+ "task_specific_params": null,
272
+ "temperature": 1.0,
273
+ "tf_legacy_loss": false,
274
+ "tie_encoder_decoder": false,
275
+ "tie_word_embeddings": true,
276
+ "tokenizer_class": null,
277
+ "top_k": 50,
278
+ "top_p": 1.0,
279
+ "torch_dtype": null,
280
+ "torchscript": false,
281
+ "transformers_version": "4.27.4",
282
+ "typical_p": 1.0,
283
+ "use_bfloat16": false
284
+ }
285
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa46759b2ef7545c1bc3f7b5c076e9055660eee88331b26cfb4d225529f8f658
3
+ size 9443768765
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afef3d90827b19571700dc3cf3ce403b34ae35cbc2137d0b772660af4115d804
3
+ size 6328861892
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff