noamrot commited on
Commit
ba26cb2
1 Parent(s): 842136c

first actual commit

Browse files
config.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "BlipFusecap"
5
+ ],
6
+ "image_text_hidden_size": 256,
7
+ "initializer_factor": 1.0,
8
+ "logit_scale_init_value": 2.6592,
9
+ "model_type": "blip",
10
+ "projection_dim": 512,
11
+ "text_config": {
12
+ "_name_or_path": "",
13
+ "add_cross_attention": false,
14
+ "architectures": null,
15
+ "attention_probs_dropout_prob": 0.0,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 30522,
19
+ "chunk_size_feed_forward": 0,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": null,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "early_stopping": false,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": 2,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "hidden_act": "gelu",
32
+ "hidden_dropout_prob": 0.0,
33
+ "hidden_size": 768,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "initializer_factor": 1.0,
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 3072,
41
+ "is_decoder": true,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "layer_norm_eps": 1e-12,
48
+ "length_penalty": 1.0,
49
+ "max_length": 60,
50
+ "max_position_embeddings": 512,
51
+ "min_length": 0,
52
+ "model_type": "blip_text_model",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 12,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 12,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": 0,
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "projection_dim": 768,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "sep_token_id": 102,
72
+ "suppress_tokens": null,
73
+ "task_specific_params": null,
74
+ "temperature": 1.0,
75
+ "tf_legacy_loss": false,
76
+ "tie_encoder_decoder": false,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_class": null,
79
+ "top_k": 50,
80
+ "top_p": 1.0,
81
+ "torch_dtype": null,
82
+ "torchscript": false,
83
+ "transformers_version": "4.26.0.dev0",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "use_cache": true,
87
+ "vocab_size": 30524
88
+ },
89
+ "torch_dtype": "float32",
90
+ "transformers_version": null,
91
+ "vision_config": {
92
+ "_name_or_path": "",
93
+ "add_cross_attention": false,
94
+ "architectures": null,
95
+ "attention_dropout": 0.0,
96
+ "bad_words_ids": null,
97
+ "begin_suppress_tokens": null,
98
+ "bos_token_id": null,
99
+ "chunk_size_feed_forward": 0,
100
+ "cross_attention_hidden_size": null,
101
+ "decoder_start_token_id": null,
102
+ "diversity_penalty": 0.0,
103
+ "do_sample": false,
104
+ "dropout": 0.0,
105
+ "early_stopping": false,
106
+ "encoder_no_repeat_ngram_size": 0,
107
+ "eos_token_id": null,
108
+ "exponential_decay_length_penalty": null,
109
+ "finetuning_task": null,
110
+ "forced_bos_token_id": null,
111
+ "forced_eos_token_id": null,
112
+ "hidden_act": "gelu",
113
+ "hidden_size": 768,
114
+ "id2label": {
115
+ "0": "LABEL_0",
116
+ "1": "LABEL_1"
117
+ },
118
+ "image_size": 384,
119
+ "initializer_factor": 1.0,
120
+ "initializer_range": 0.02,
121
+ "intermediate_size": 3072,
122
+ "is_decoder": false,
123
+ "is_encoder_decoder": false,
124
+ "label2id": {
125
+ "LABEL_0": 0,
126
+ "LABEL_1": 1
127
+ },
128
+ "layer_norm_eps": 1e-05,
129
+ "length_penalty": 1.0,
130
+ "max_length": 20,
131
+ "min_length": 0,
132
+ "model_type": "blip_vision_model",
133
+ "no_repeat_ngram_size": 0,
134
+ "num_attention_heads": 12,
135
+ "num_beam_groups": 1,
136
+ "num_beams": 1,
137
+ "num_channels": 3,
138
+ "num_hidden_layers": 12,
139
+ "num_return_sequences": 1,
140
+ "output_attentions": false,
141
+ "output_hidden_states": false,
142
+ "output_scores": false,
143
+ "pad_token_id": null,
144
+ "patch_size": 16,
145
+ "prefix": null,
146
+ "problem_type": null,
147
+ "projection_dim": 512,
148
+ "pruned_heads": {},
149
+ "remove_invalid_values": false,
150
+ "repetition_penalty": 1.0,
151
+ "return_dict": true,
152
+ "return_dict_in_generate": false,
153
+ "sep_token_id": null,
154
+ "suppress_tokens": null,
155
+ "task_specific_params": null,
156
+ "temperature": 1.0,
157
+ "tf_legacy_loss": false,
158
+ "tie_encoder_decoder": false,
159
+ "tie_word_embeddings": true,
160
+ "tokenizer_class": null,
161
+ "top_k": 50,
162
+ "top_p": 1.0,
163
+ "torch_dtype": null,
164
+ "torchscript": false,
165
+ "transformers_version": "4.26.0.dev0",
166
+ "typical_p": 1.0,
167
+ "use_bfloat16": false
168
+ }
169
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_resize": true,
4
+ "image_mean": [
5
+ 0.48145466,
6
+ 0.4578275,
7
+ 0.40821073
8
+ ],
9
+ "image_processor_type": "BlipFuseCapImageProcessor",
10
+ "image_std": [
11
+ 0.26862954,
12
+ 0.26130258,
13
+ 0.27577711
14
+ ],
15
+ "processor_class": "BlipFuseCapProcessor",
16
+ "size": 384
17
+ }
requirements.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ timm==0.4.12
2
+ transformers==4.15.0
3
+ fairscale==0.4.4
4
+ torch
5
+ torchvision
6
+ Pillow
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "name_or_path": "bert-base-uncased",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "processor_class": "BlipFuseCapProcessor",
11
+ "sep_token": "[SEP]",
12
+ "special_tokens_map_file": null,
13
+ "strip_accents": null,
14
+ "tokenize_chinese_chars": true,
15
+ "tokenizer_class": "BertTokenizer",
16
+ "unk_token": "[UNK]",
17
+ "model_input_names": [
18
+ "input_ids",
19
+ "attention_mask"
20
+ ]
21
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff