nielsr HF staff commited on
Commit
e27f1f9
1 Parent(s): c7b85ae

Upload Blip2ForConditionalGeneration

Browse files
config.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "Blip2ForConditionalGeneration"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "initializer_range": 0.02,
8
+ "model_type": "blip-2",
9
+ "num_query_tokens": 32,
10
+ "qformer_config": {
11
+ "_name_or_path": "",
12
+ "add_cross_attention": false,
13
+ "architectures": null,
14
+ "attention_probs_dropout_prob": 0.1,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": null,
18
+ "chunk_size_feed_forward": 0,
19
+ "classifier_dropout": null,
20
+ "cross_attention_frequency": 2,
21
+ "cross_attention_hidden_size": null,
22
+ "decoder_start_token_id": null,
23
+ "diversity_penalty": 0.0,
24
+ "do_sample": false,
25
+ "early_stopping": false,
26
+ "encoder_hidden_size": 1408,
27
+ "encoder_no_repeat_ngram_size": 0,
28
+ "eos_token_id": null,
29
+ "exponential_decay_length_penalty": null,
30
+ "finetuning_task": null,
31
+ "forced_bos_token_id": null,
32
+ "forced_eos_token_id": null,
33
+ "hidden_act": "gelu",
34
+ "hidden_dropout_prob": 0.1,
35
+ "hidden_size": 768,
36
+ "id2label": {
37
+ "0": "LABEL_0",
38
+ "1": "LABEL_1"
39
+ },
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 3072,
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-12,
49
+ "length_penalty": 1.0,
50
+ "max_length": 20,
51
+ "max_position_embeddings": 512,
52
+ "min_length": 0,
53
+ "model_type": "blip_2_qformer",
54
+ "no_repeat_ngram_size": 0,
55
+ "num_attention_heads": 12,
56
+ "num_beam_groups": 1,
57
+ "num_beams": 1,
58
+ "num_hidden_layers": 12,
59
+ "num_return_sequences": 1,
60
+ "output_attentions": false,
61
+ "output_hidden_states": false,
62
+ "output_scores": false,
63
+ "pad_token_id": 0,
64
+ "position_embedding_type": "absolute",
65
+ "prefix": null,
66
+ "problem_type": null,
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": 30522
88
+ },
89
+ "text_config": {
90
+ "_name_or_path": "",
91
+ "_remove_final_layer_norm": false,
92
+ "activation_dropout": 0.0,
93
+ "activation_function": "relu",
94
+ "add_cross_attention": false,
95
+ "architectures": [
96
+ "OPTForCausalLM"
97
+ ],
98
+ "attention_dropout": 0.0,
99
+ "bad_words_ids": null,
100
+ "begin_suppress_tokens": null,
101
+ "bos_token_id": 2,
102
+ "chunk_size_feed_forward": 0,
103
+ "cross_attention_hidden_size": null,
104
+ "decoder_start_token_id": null,
105
+ "diversity_penalty": 0.0,
106
+ "do_layer_norm_before": true,
107
+ "do_sample": false,
108
+ "dropout": 0.1,
109
+ "early_stopping": false,
110
+ "enable_bias": true,
111
+ "encoder_no_repeat_ngram_size": 0,
112
+ "eos_token_id": 50118,
113
+ "exponential_decay_length_penalty": null,
114
+ "ffn_dim": 16384,
115
+ "finetuning_task": null,
116
+ "forced_bos_token_id": null,
117
+ "forced_eos_token_id": null,
118
+ "hidden_size": 4096,
119
+ "id2label": {
120
+ "0": "LABEL_0",
121
+ "1": "LABEL_1"
122
+ },
123
+ "init_std": 0.02,
124
+ "is_decoder": false,
125
+ "is_encoder_decoder": false,
126
+ "label2id": {
127
+ "LABEL_0": 0,
128
+ "LABEL_1": 1
129
+ },
130
+ "layer_norm_elementwise_affine": true,
131
+ "layerdrop": 0.0,
132
+ "length_penalty": 1.0,
133
+ "max_length": 20,
134
+ "max_position_embeddings": 2048,
135
+ "min_length": 0,
136
+ "model_type": "opt",
137
+ "no_repeat_ngram_size": 0,
138
+ "num_attention_heads": 32,
139
+ "num_beam_groups": 1,
140
+ "num_beams": 1,
141
+ "num_hidden_layers": 32,
142
+ "num_return_sequences": 1,
143
+ "output_attentions": false,
144
+ "output_hidden_states": false,
145
+ "output_scores": false,
146
+ "pad_token_id": 1,
147
+ "prefix": "</s>",
148
+ "problem_type": null,
149
+ "pruned_heads": {},
150
+ "remove_invalid_values": false,
151
+ "repetition_penalty": 1.0,
152
+ "return_dict": true,
153
+ "return_dict_in_generate": false,
154
+ "sep_token_id": null,
155
+ "suppress_tokens": null,
156
+ "task_specific_params": null,
157
+ "temperature": 1.0,
158
+ "tf_legacy_loss": false,
159
+ "tie_encoder_decoder": false,
160
+ "tie_word_embeddings": true,
161
+ "tokenizer_class": null,
162
+ "top_k": 50,
163
+ "top_p": 1.0,
164
+ "torch_dtype": "float16",
165
+ "torchscript": false,
166
+ "transformers_version": "4.27.0.dev0",
167
+ "typical_p": 1.0,
168
+ "use_bfloat16": false,
169
+ "use_cache": true,
170
+ "vocab_size": 50272,
171
+ "word_embed_proj_dim": 4096
172
+ },
173
+ "torch_dtype": "float32",
174
+ "transformers_version": null,
175
+ "use_decoder_only_language_model": true,
176
+ "vision_config": {
177
+ "_name_or_path": "",
178
+ "add_cross_attention": false,
179
+ "architectures": null,
180
+ "attention_dropout": 0.0,
181
+ "bad_words_ids": null,
182
+ "begin_suppress_tokens": null,
183
+ "bos_token_id": null,
184
+ "chunk_size_feed_forward": 0,
185
+ "cross_attention_hidden_size": null,
186
+ "decoder_start_token_id": null,
187
+ "diversity_penalty": 0.0,
188
+ "do_sample": false,
189
+ "dropout": 0.0,
190
+ "early_stopping": false,
191
+ "encoder_no_repeat_ngram_size": 0,
192
+ "eos_token_id": null,
193
+ "exponential_decay_length_penalty": null,
194
+ "finetuning_task": null,
195
+ "forced_bos_token_id": null,
196
+ "forced_eos_token_id": null,
197
+ "hidden_act": "gelu",
198
+ "hidden_size": 1408,
199
+ "id2label": {
200
+ "0": "LABEL_0",
201
+ "1": "LABEL_1"
202
+ },
203
+ "image_size": 364,
204
+ "initializer_factor": 1.0,
205
+ "initializer_range": 1e-10,
206
+ "intermediate_size": 6144,
207
+ "is_decoder": false,
208
+ "is_encoder_decoder": false,
209
+ "label2id": {
210
+ "LABEL_0": 0,
211
+ "LABEL_1": 1
212
+ },
213
+ "layer_norm_eps": 1e-05,
214
+ "length_penalty": 1.0,
215
+ "max_length": 20,
216
+ "min_length": 0,
217
+ "model_type": "blip_2_vision_model",
218
+ "no_repeat_ngram_size": 0,
219
+ "num_attention_heads": 16,
220
+ "num_beam_groups": 1,
221
+ "num_beams": 1,
222
+ "num_channels": 3,
223
+ "num_hidden_layers": 39,
224
+ "num_return_sequences": 1,
225
+ "output_attentions": false,
226
+ "output_hidden_states": false,
227
+ "output_scores": false,
228
+ "pad_token_id": null,
229
+ "patch_size": 14,
230
+ "prefix": null,
231
+ "problem_type": null,
232
+ "projection_dim": 512,
233
+ "pruned_heads": {},
234
+ "qkv_bias": true,
235
+ "remove_invalid_values": false,
236
+ "repetition_penalty": 1.0,
237
+ "return_dict": true,
238
+ "return_dict_in_generate": false,
239
+ "sep_token_id": null,
240
+ "suppress_tokens": null,
241
+ "task_specific_params": null,
242
+ "temperature": 1.0,
243
+ "tf_legacy_loss": false,
244
+ "tie_encoder_decoder": false,
245
+ "tie_word_embeddings": true,
246
+ "tokenizer_class": null,
247
+ "top_k": 50,
248
+ "top_p": 1.0,
249
+ "torch_dtype": null,
250
+ "torchscript": false,
251
+ "transformers_version": "4.27.0.dev0",
252
+ "typical_p": 1.0,
253
+ "use_bfloat16": false
254
+ }
255
+ }
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b79bceccf5d42c2eb50a5e881d2c66ab12155638c17a74b0b49ab4060b6961
3
+ size 9801426073
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2108f77ba152c5921e7f1a357c5f59ea71e084c250252e491d20f1b343b8c46c
3
+ size 9934790547
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e6a38430e6d4b0c3cd75a332b190dbcfd15c0c86f0ada4df144c58cc8e7e337
3
+ size 9934842089
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d19ef7fbc256eadf222b928821245d29b2eafd708482266396c499dc8a52fe
3
+ size 2166169773
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff