Hugging Face's logo

OpenGVLab
/
ASM-Pretrain

Transformers
PyTorch
blip-2
Inference Endpoints
Model card Files Community
Weiyun1025 commited on
Commit
362d2ea
•
1 Parent(s): e6ae5d4

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. added_tokens.json +5 -0
  2. config.json +307 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.model +3 -0
  6. tokenizer_config.json +33 -0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</img>": 32001,
3
+ "<ImageContent>": 32002,
4
+ "<img>": 32000
5
+ }
config.json ADDED
@@ -0,0 +1,307 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/mnt/petrelfs/share_data/zhangqinglong/Husky/work_dirs/husky-7b-v0_01",
4
+ "aligned": true,
5
+ "architectures": [
6
+ "UnifiedHuskyFlattenCat"
7
+ ],
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_size": 4096,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "lora": false,
14
+ "lora_vision": false,
15
+ "model_type": "blip-2",
16
+ "num_query_tokens": 32,
17
+ "output_size": [
18
+ 7,
19
+ 7
20
+ ],
21
+ "pad_token_id": 0,
22
+ "prompt_length": 5,
23
+ "qformer_config": {
24
+ "_name_or_path": "",
25
+ "add_cross_attention": false,
26
+ "architectures": null,
27
+ "attention_probs_dropout_prob": 0.1,
28
+ "bad_words_ids": null,
29
+ "begin_suppress_tokens": null,
30
+ "bos_token_id": null,
31
+ "chunk_size_feed_forward": 0,
32
+ "classifier_dropout": null,
33
+ "cross_attention_frequency": 2,
34
+ "cross_attention_hidden_size": null,
35
+ "decoder_start_token_id": null,
36
+ "diversity_penalty": 0.0,
37
+ "do_sample": false,
38
+ "early_stopping": false,
39
+ "encoder_hidden_size": 1408,
40
+ "encoder_no_repeat_ngram_size": 0,
41
+ "eos_token_id": null,
42
+ "exponential_decay_length_penalty": null,
43
+ "finetuning_task": null,
44
+ "forced_bos_token_id": null,
45
+ "forced_eos_token_id": null,
46
+ "hidden_act": "gelu",
47
+ "hidden_dropout_prob": 0.1,
48
+ "hidden_size": 768,
49
+ "id2label": {
50
+ "0": "LABEL_0",
51
+ "1": "LABEL_1"
52
+ },
53
+ "initializer_range": 0.02,
54
+ "intermediate_size": 3072,
55
+ "is_decoder": false,
56
+ "is_encoder_decoder": false,
57
+ "label2id": {
58
+ "LABEL_0": 0,
59
+ "LABEL_1": 1
60
+ },
61
+ "layer_norm_eps": 1e-12,
62
+ "length_penalty": 1.0,
63
+ "max_length": 20,
64
+ "max_position_embeddings": 512,
65
+ "min_length": 0,
66
+ "model_type": "blip_2_qformer",
67
+ "no_repeat_ngram_size": 0,
68
+ "num_attention_heads": 12,
69
+ "num_beam_groups": 1,
70
+ "num_beams": 1,
71
+ "num_hidden_layers": 12,
72
+ "num_return_sequences": 1,
73
+ "output_attentions": false,
74
+ "output_hidden_states": false,
75
+ "output_scores": false,
76
+ "pad_token_id": 0,
77
+ "position_embedding_type": "absolute",
78
+ "prefix": null,
79
+ "problem_type": null,
80
+ "pruned_heads": {},
81
+ "remove_invalid_values": false,
82
+ "repetition_penalty": 1.0,
83
+ "return_dict": true,
84
+ "return_dict_in_generate": false,
85
+ "sep_token_id": null,
86
+ "suppress_tokens": null,
87
+ "task_specific_params": null,
88
+ "temperature": 1.0,
89
+ "tf_legacy_loss": false,
90
+ "tie_encoder_decoder": false,
91
+ "tie_word_embeddings": true,
92
+ "tokenizer_class": null,
93
+ "top_k": 50,
94
+ "top_p": 1.0,
95
+ "torch_dtype": null,
96
+ "torchscript": false,
97
+ "transformers_version": "4.28.0",
98
+ "typical_p": 1.0,
99
+ "use_bfloat16": false,
100
+ "vocab_size": 30522
101
+ },
102
+ "sampling_ratio": -1,
103
+ "text_config": {
104
+ "_name_or_path": "",
105
+ "add_cross_attention": false,
106
+ "architectures": [
107
+ "LlamaForCausalLM"
108
+ ],
109
+ "bad_words_ids": null,
110
+ "begin_suppress_tokens": null,
111
+ "bos_token_id": 1,
112
+ "chunk_size_feed_forward": 0,
113
+ "cross_attention_hidden_size": null,
114
+ "decoder_start_token_id": null,
115
+ "diversity_penalty": 0.0,
116
+ "do_sample": false,
117
+ "early_stopping": false,
118
+ "encoder_no_repeat_ngram_size": 0,
119
+ "eos_token_id": 2,
120
+ "exponential_decay_length_penalty": null,
121
+ "finetuning_task": null,
122
+ "forced_bos_token_id": null,
123
+ "forced_eos_token_id": null,
124
+ "hidden_act": "silu",
125
+ "hidden_size": 4096,
126
+ "id2label": {
127
+ "0": "LABEL_0",
128
+ "1": "LABEL_1"
129
+ },
130
+ "initializer_range": 0.02,
131
+ "intermediate_size": 11008,
132
+ "is_decoder": false,
133
+ "is_encoder_decoder": false,
134
+ "label2id": {
135
+ "LABEL_0": 0,
136
+ "LABEL_1": 1
137
+ },
138
+ "length_penalty": 1.0,
139
+ "max_length": 20,
140
+ "max_position_embeddings": 2048,
141
+ "max_sequence_length": 2048,
142
+ "min_length": 0,
143
+ "model_type": "llama",
144
+ "no_repeat_ngram_size": 0,
145
+ "num_attention_heads": 32,
146
+ "num_beam_groups": 1,
147
+ "num_beams": 1,
148
+ "num_hidden_layers": 32,
149
+ "num_return_sequences": 1,
150
+ "output_attentions": false,
151
+ "output_hidden_states": false,
152
+ "output_scores": false,
153
+ "pad_token_id": 0,
154
+ "prefix": null,
155
+ "problem_type": null,
156
+ "pruned_heads": {},
157
+ "remove_invalid_values": false,
158
+ "repetition_penalty": 1.0,
159
+ "return_dict": true,
160
+ "return_dict_in_generate": false,
161
+ "rms_norm_eps": 1e-06,
162
+ "sep_token_id": null,
163
+ "suppress_tokens": null,
164
+ "task_specific_params": null,
165
+ "temperature": 1.0,
166
+ "tf_legacy_loss": false,
167
+ "tie_encoder_decoder": false,
168
+ "tie_word_embeddings": false,
169
+ "tokenizer_class": null,
170
+ "top_k": 50,
171
+ "top_p": 1.0,
172
+ "torch_dtype": "float16",
173
+ "torchscript": false,
174
+ "transformers_version": "4.28.0",
175
+ "typical_p": 1.0,
176
+ "use_bfloat16": false,
177
+ "use_cache": true,
178
+ "vocab_size": 32003
179
+ },
180
+ "tie_word_embeddings": false,
181
+ "torch_dtype": "bfloat16",
182
+ "transformers_version": null,
183
+ "use_cache": false,
184
+ "use_decoder_only_language_model": true,
185
+ "use_window_attn": null,
186
+ "vision_config": {
187
+ "_name_or_path": "",
188
+ "add_cross_attention": false,
189
+ "architectures": null,
190
+ "attention_dropout": 0.0,
191
+ "bad_words_ids": null,
192
+ "begin_suppress_tokens": null,
193
+ "bos_token_id": null,
194
+ "chunk_size_feed_forward": 0,
195
+ "cross_attention_hidden_size": null,
196
+ "decoder_start_token_id": null,
197
+ "diversity_penalty": 0.0,
198
+ "do_sample": false,
199
+ "dropout": 0.0,
200
+ "early_stopping": false,
201
+ "encoder_no_repeat_ngram_size": 0,
202
+ "eos_token_id": null,
203
+ "exponential_decay_length_penalty": null,
204
+ "finetuning_task": null,
205
+ "forced_bos_token_id": null,
206
+ "forced_eos_token_id": null,
207
+ "hidden_act": "gelu",
208
+ "hidden_size": 1408,
209
+ "id2label": {
210
+ "0": "LABEL_0",
211
+ "1": "LABEL_1"
212
+ },
213
+ "image_size": 224,
214
+ "initializer_factor": 1.0,
215
+ "initializer_range": 1e-10,
216
+ "intermediate_size": 6144,
217
+ "is_decoder": false,
218
+ "is_encoder_decoder": false,
219
+ "label2id": {
220
+ "LABEL_0": 0,
221
+ "LABEL_1": 1
222
+ },
223
+ "layer_norm_eps": 1e-05,
224
+ "length_penalty": 1.0,
225
+ "max_length": 20,
226
+ "min_length": 0,
227
+ "model_type": "blip_2_vision_model",
228
+ "no_repeat_ngram_size": 0,
229
+ "num_attention_heads": 16,
230
+ "num_beam_groups": 1,
231
+ "num_beams": 1,
232
+ "num_channels": 3,
233
+ "num_hidden_layers": 39,
234
+ "num_return_sequences": 1,
235
+ "output_attentions": false,
236
+ "output_hidden_states": false,
237
+ "output_scores": false,
238
+ "pad_token_id": null,
239
+ "patch_size": 14,
240
+ "prefix": null,
241
+ "problem_type": null,
242
+ "projection_dim": 512,
243
+ "pruned_heads": {},
244
+ "qkv_bias": true,
245
+ "remove_invalid_values": false,
246
+ "repetition_penalty": 1.0,
247
+ "return_dict": true,
248
+ "return_dict_in_generate": false,
249
+ "sep_token_id": null,
250
+ "suppress_tokens": null,
251
+ "task_specific_params": null,
252
+ "temperature": 1.0,
253
+ "tf_legacy_loss": false,
254
+ "tie_encoder_decoder": false,
255
+ "tie_word_embeddings": true,
256
+ "tokenizer_class": null,
257
+ "top_k": 50,
258
+ "top_p": 1.0,
259
+ "torch_dtype": null,
260
+ "torchscript": false,
261
+ "transformers_version": "4.28.0",
262
+ "typical_p": 1.0,
263
+ "use_bfloat16": false
264
+ },
265
+ "window_attn": [
266
+ false,
267
+ false,
268
+ false,
269
+ false,
270
+ false,
271
+ false,
272
+ false,
273
+ false,
274
+ false,
275
+ false,
276
+ false,
277
+ false,
278
+ false,
279
+ false,
280
+ false,
281
+ false,
282
+ false,
283
+ false,
284
+ false,
285
+ false,
286
+ false,
287
+ false,
288
+ false,
289
+ false,
290
+ false,
291
+ false,
292
+ false,
293
+ false,
294
+ false,
295
+ false,
296
+ false,
297
+ false,
298
+ false,
299
+ false,
300
+ false,
301
+ false,
302
+ false,
303
+ false,
304
+ false
305
+ ],
306
+ "window_size": 16
307
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7c0fea1ae289a8a7c4d2236fbead7418217bd46230cce3dc26dc9ecd417ff94
3
+ size 15818753235
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "pad_token": null,
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }