Hugging Face's logo

Salesforce
/
blip-image-captioning-large

Image-to-Text Transformers PyTorch TensorFlow Safetensors blip text2text-generation image-captioning Inference Endpoints
Model card Files Community
31
ybelkada HF staff commited on
Commit
1d75d8b
•
1 Parent(s): eb32014

Upload BlipForConditionalGeneration

Browse files
Files changed (2) hide show
  1. config.json +170 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "BlipForConditionalGeneration"
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_hidden_size": 1024,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": 2,
28
+ "exponential_decay_length_penalty": null,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": null,
31
+ "forced_eos_token_id": null,
32
+ "hidden_act": "gelu",
33
+ "hidden_dropout_prob": 0.0,
34
+ "hidden_size": 768,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1"
38
+ },
39
+ "initializer_factor": 1.0,
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 3072,
42
+ "is_decoder": true,
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_text_model",
54
+ "no_repeat_ngram_size": 0,
55
+ "num_attention_heads": 8,
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
+ "prefix": null,
65
+ "problem_type": null,
66
+ "projection_dim": 768,
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": 102,
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": "4.26.0.dev0",
85
+ "typical_p": 1.0,
86
+ "use_bfloat16": false,
87
+ "use_cache": true,
88
+ "vocab_size": 30524
89
+ },
90
+ "torch_dtype": "float32",
91
+ "transformers_version": null,
92
+ "vision_config": {
93
+ "_name_or_path": "",
94
+ "add_cross_attention": false,
95
+ "architectures": null,
96
+ "attention_dropout": 0.0,
97
+ "bad_words_ids": null,
98
+ "begin_suppress_tokens": null,
99
+ "bos_token_id": null,
100
+ "chunk_size_feed_forward": 0,
101
+ "cross_attention_hidden_size": null,
102
+ "decoder_start_token_id": null,
103
+ "diversity_penalty": 0.0,
104
+ "do_sample": false,
105
+ "dropout": 0.0,
106
+ "early_stopping": false,
107
+ "encoder_no_repeat_ngram_size": 0,
108
+ "eos_token_id": null,
109
+ "exponential_decay_length_penalty": null,
110
+ "finetuning_task": null,
111
+ "forced_bos_token_id": null,
112
+ "forced_eos_token_id": null,
113
+ "hidden_act": "gelu",
114
+ "hidden_size": 1024,
115
+ "id2label": {
116
+ "0": "LABEL_0",
117
+ "1": "LABEL_1"
118
+ },
119
+ "image_size": 384,
120
+ "initializer_factor": 1.0,
121
+ "initializer_range": 0.02,
122
+ "intermediate_size": 4096,
123
+ "is_decoder": false,
124
+ "is_encoder_decoder": false,
125
+ "label2id": {
126
+ "LABEL_0": 0,
127
+ "LABEL_1": 1
128
+ },
129
+ "layer_norm_eps": 1e-05,
130
+ "length_penalty": 1.0,
131
+ "max_length": 20,
132
+ "min_length": 0,
133
+ "model_type": "blip_vision_model",
134
+ "no_repeat_ngram_size": 0,
135
+ "num_attention_heads": 16,
136
+ "num_beam_groups": 1,
137
+ "num_beams": 1,
138
+ "num_channels": 3,
139
+ "num_hidden_layers": 24,
140
+ "num_return_sequences": 1,
141
+ "output_attentions": false,
142
+ "output_hidden_states": false,
143
+ "output_scores": false,
144
+ "pad_token_id": null,
145
+ "patch_size": 16,
146
+ "prefix": null,
147
+ "problem_type": null,
148
+ "projection_dim": 512,
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": null,
165
+ "torchscript": false,
166
+ "transformers_version": "4.26.0.dev0",
167
+ "typical_p": 1.0,
168
+ "use_bfloat16": false
169
+ }
170
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66c8aec8d91b5e74b86bde343ed95fb53e9ccf9ffc77c5093890df662d234e04
3
+ size 1879143921