yhyu13 commited on
Commit
ca85c9d
1 Parent(s): 3e9c496
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "InstructBlipForConditionalGeneration"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "initializer_range": 0.02,
8
+ "model_type": "instructblip",
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": "instructblip_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": "4.30.0.dev0",
85
+ "typical_p": 1.0,
86
+ "use_bfloat16": false,
87
+ "vocab_size": 30523
88
+ },
89
+ "text_config": {
90
+ "_name_or_path": "",
91
+ "add_cross_attention": false,
92
+ "architectures": [
93
+ "LLaMAForCausalLM"
94
+ ],
95
+ "bad_words_ids": null,
96
+ "begin_suppress_tokens": null,
97
+ "bos_token_id": 0,
98
+ "chunk_size_feed_forward": 0,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "early_stopping": false,
104
+ "encoder_no_repeat_ngram_size": 0,
105
+ "eos_token_id": 1,
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": "silu",
111
+ "hidden_size": 4096,
112
+ "id2label": {
113
+ "0": "LABEL_0",
114
+ "1": "LABEL_1"
115
+ },
116
+ "initializer_range": 0.02,
117
+ "intermediate_size": 11008,
118
+ "is_decoder": false,
119
+ "is_encoder_decoder": false,
120
+ "label2id": {
121
+ "LABEL_0": 0,
122
+ "LABEL_1": 1
123
+ },
124
+ "length_penalty": 1.0,
125
+ "max_length": 20,
126
+ "max_position_embeddings": 2048,
127
+ "max_sequence_length": 2048,
128
+ "min_length": 0,
129
+ "model_type": "llama",
130
+ "no_repeat_ngram_size": 0,
131
+ "num_attention_heads": 32,
132
+ "num_beam_groups": 1,
133
+ "num_beams": 1,
134
+ "num_hidden_layers": 32,
135
+ "num_return_sequences": 1,
136
+ "output_attentions": false,
137
+ "output_hidden_states": false,
138
+ "output_scores": false,
139
+ "pad_token_id": -1,
140
+ "prefix": null,
141
+ "problem_type": null,
142
+ "pruned_heads": {},
143
+ "remove_invalid_values": false,
144
+ "repetition_penalty": 1.0,
145
+ "return_dict": true,
146
+ "return_dict_in_generate": false,
147
+ "rms_norm_eps": 1e-06,
148
+ "sep_token_id": null,
149
+ "suppress_tokens": null,
150
+ "task_specific_params": null,
151
+ "temperature": 1.0,
152
+ "tf_legacy_loss": false,
153
+ "tie_encoder_decoder": false,
154
+ "tie_word_embeddings": false,
155
+ "tokenizer_class": null,
156
+ "top_k": 50,
157
+ "top_p": 1.0,
158
+ "torch_dtype": "float16",
159
+ "torchscript": false,
160
+ "transformers_version": "4.30.0.dev0",
161
+ "typical_p": 1.0,
162
+ "use_bfloat16": false,
163
+ "use_cache": true,
164
+ "vocab_size": 32001
165
+ },
166
+ "tie_word_embeddings": false,
167
+ "torch_dtype": "float32",
168
+ "transformers_version": null,
169
+ "use_decoder_only_language_model": true,
170
+ "vision_config": {
171
+ "_name_or_path": "",
172
+ "add_cross_attention": false,
173
+ "architectures": null,
174
+ "attention_dropout": 0.0,
175
+ "bad_words_ids": null,
176
+ "begin_suppress_tokens": null,
177
+ "bos_token_id": null,
178
+ "chunk_size_feed_forward": 0,
179
+ "cross_attention_hidden_size": null,
180
+ "decoder_start_token_id": null,
181
+ "diversity_penalty": 0.0,
182
+ "do_sample": false,
183
+ "dropout": 0.0,
184
+ "early_stopping": false,
185
+ "encoder_no_repeat_ngram_size": 0,
186
+ "eos_token_id": null,
187
+ "exponential_decay_length_penalty": null,
188
+ "finetuning_task": null,
189
+ "forced_bos_token_id": null,
190
+ "forced_eos_token_id": null,
191
+ "hidden_act": "gelu",
192
+ "hidden_size": 1408,
193
+ "id2label": {
194
+ "0": "LABEL_0",
195
+ "1": "LABEL_1"
196
+ },
197
+ "image_size": 224,
198
+ "initializer_factor": 1.0,
199
+ "initializer_range": 1e-10,
200
+ "intermediate_size": 6144,
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-06,
208
+ "length_penalty": 1.0,
209
+ "max_length": 20,
210
+ "min_length": 0,
211
+ "model_type": "instructblip_vision_model",
212
+ "no_repeat_ngram_size": 0,
213
+ "num_attention_heads": 16,
214
+ "num_beam_groups": 1,
215
+ "num_beams": 1,
216
+ "num_channels": 3,
217
+ "num_hidden_layers": 39,
218
+ "num_return_sequences": 1,
219
+ "output_attentions": false,
220
+ "output_hidden_states": false,
221
+ "output_scores": false,
222
+ "pad_token_id": null,
223
+ "patch_size": 14,
224
+ "prefix": null,
225
+ "problem_type": null,
226
+ "projection_dim": 512,
227
+ "pruned_heads": {},
228
+ "qkv_bias": true,
229
+ "remove_invalid_values": false,
230
+ "repetition_penalty": 1.0,
231
+ "return_dict": true,
232
+ "return_dict_in_generate": false,
233
+ "sep_token_id": null,
234
+ "suppress_tokens": null,
235
+ "task_specific_params": null,
236
+ "temperature": 1.0,
237
+ "tf_legacy_loss": false,
238
+ "tie_encoder_decoder": false,
239
+ "tie_word_embeddings": true,
240
+ "tokenizer_class": null,
241
+ "top_k": 50,
242
+ "top_p": 1.0,
243
+ "torch_dtype": null,
244
+ "torchscript": false,
245
+ "transformers_version": "4.30.0.dev0",
246
+ "typical_p": 1.0,
247
+ "use_bfloat16": false
248
+ }
249
+ }
instructblip-vicuna-7b-4bit-128g-no-actor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acd317ad05808d678c10abaa6b8f4ba680f06d57b15ed16d347909f467a1d145
3
+ size 4418803368
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "BlipImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "processor_class": "InstructBlipProcessor",
18
+ "resample": 3,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ }
24
+ }
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff
 
qformer_tokenizer/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[DEC]": 30522
3
+ }
qformer_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[DEC]",
3
+ "cls_token": "[CLS]",
4
+ "mask_token": "[MASK]",
5
+ "pad_token": "[PAD]",
6
+ "sep_token": "[SEP]",
7
+ "unk_token": "[UNK]"
8
+ }
qformer_tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
qformer_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "BertTokenizer",
12
+ "truncation_side": "left",
13
+ "unk_token": "[UNK]"
14
+ }
qformer_tokenizer/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "</s>",
3
+ "eos_token": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "pad_token": "[PAD]",
11
+ "unk_token": "</s>"
12
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "</s>",
3
+ "clean_up_tokenization_spaces": false,
4
+ "eos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "</s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "model_max_length": 2048,
13
+ "pad_token": null,
14
+ "processor_class": "InstructBlipProcessor",
15
+ "sp_model_kwargs": {},
16
+ "tokenizer_class": "LlamaTokenizer",
17
+ "truncation_side": "left",
18
+ "unk_token": "</s>"
19
+ }