Hugging Face's logo

podonamu
/
blip-image-captioning-base-insta-test

Image-Text-to-Text
Transformers
PyTorch
TensorBoard
blip
Generated from Trainer
Model card Files
xet
 Metrics Community
1
podonamu commited on
Commit
e4a846e
·
1 Parent(s): 59c3e49

Model save

Browse files
Files changed (11) hide show
  1. .gitignore +1 -0
  2. config.json +172 -0
  3. pytorch_model.bin +3 -0
  4. runs/Jun06_04-04-49_75fada0359be/events.out.tfevents.1717646848.75fada0359be.174.0 +3 -0
  5. runs/Jun06_04-17-39_75fada0359be/events.out.tfevents.1717647469.75fada0359be.174.1 +3 -0
  6. runs/Jun06_04-23-04_75fada0359be/events.out.tfevents.1717647796.75fada0359be.174.2 +3 -0
  7. runs/Jun06_04-53-09_75fada0359be/events.out.tfevents.1717649654.75fada0359be.174.3 +3 -0
  8. runs/Jun06_04-56-09_75fada0359be/events.out.tfevents.1717649773.75fada0359be.174.4 +3 -0
  9. runs/Jun06_05-12-26_75fada0359be/events.out.tfevents.1717650761.75fada0359be.174.5 +3 -0
  10. runs/Jun06_05-27-35_75fada0359be/events.out.tfevents.1717651670.75fada0359be.174.6 +3 -0
  11. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,172 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "89b09ea1789f7addf2f6d6f0dfc4ce10ab58ef84",
3
+ "_name_or_path": "Salesforce/blip-image-captioning-base",
4
+ "architectures": [
5
+ "BlipForConditionalGeneration"
6
+ ],
7
+ "image_text_hidden_size": 256,
8
+ "initializer_factor": 1.0,
9
+ "initializer_range": 0.02,
10
+ "logit_scale_init_value": 2.6592,
11
+ "model_type": "blip",
12
+ "projection_dim": 512,
13
+ "text_config": {
14
+ "_name_or_path": "",
15
+ "add_cross_attention": false,
16
+ "architectures": null,
17
+ "attention_probs_dropout_prob": 0.0,
18
+ "bad_words_ids": null,
19
+ "begin_suppress_tokens": null,
20
+ "bos_token_id": 30522,
21
+ "chunk_size_feed_forward": 0,
22
+ "cross_attention_hidden_size": null,
23
+ "decoder_start_token_id": null,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "early_stopping": false,
27
+ "encoder_hidden_size": 768,
28
+ "encoder_no_repeat_ngram_size": 0,
29
+ "eos_token_id": 2,
30
+ "exponential_decay_length_penalty": null,
31
+ "finetuning_task": null,
32
+ "forced_bos_token_id": null,
33
+ "forced_eos_token_id": null,
34
+ "hidden_act": "gelu",
35
+ "hidden_dropout_prob": 0.0,
36
+ "hidden_size": 768,
37
+ "id2label": {
38
+ "0": "LABEL_0",
39
+ "1": "LABEL_1"
40
+ },
41
+ "initializer_factor": 1.0,
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 3072,
44
+ "is_decoder": true,
45
+ "is_encoder_decoder": false,
46
+ "label2id": {
47
+ "LABEL_0": 0,
48
+ "LABEL_1": 1
49
+ },
50
+ "layer_norm_eps": 1e-12,
51
+ "length_penalty": 1.0,
52
+ "max_length": 20,
53
+ "max_position_embeddings": 512,
54
+ "min_length": 0,
55
+ "model_type": "blip_text_model",
56
+ "no_repeat_ngram_size": 0,
57
+ "num_attention_heads": 12,
58
+ "num_beam_groups": 1,
59
+ "num_beams": 1,
60
+ "num_hidden_layers": 12,
61
+ "num_return_sequences": 1,
62
+ "output_attentions": false,
63
+ "output_hidden_states": false,
64
+ "output_scores": false,
65
+ "pad_token_id": 0,
66
+ "prefix": null,
67
+ "problem_type": null,
68
+ "projection_dim": 768,
69
+ "pruned_heads": {},
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "return_dict": true,
73
+ "return_dict_in_generate": false,
74
+ "sep_token_id": 102,
75
+ "suppress_tokens": null,
76
+ "task_specific_params": null,
77
+ "temperature": 1.0,
78
+ "tf_legacy_loss": false,
79
+ "tie_encoder_decoder": false,
80
+ "tie_word_embeddings": true,
81
+ "tokenizer_class": null,
82
+ "top_k": 50,
83
+ "top_p": 1.0,
84
+ "torch_dtype": null,
85
+ "torchscript": false,
86
+ "transformers_version": "4.30.1",
87
+ "typical_p": 1.0,
88
+ "use_bfloat16": false,
89
+ "use_cache": true,
90
+ "vocab_size": 30524
91
+ },
92
+ "torch_dtype": "float32",
93
+ "transformers_version": null,
94
+ "vision_config": {
95
+ "_name_or_path": "",
96
+ "add_cross_attention": false,
97
+ "architectures": null,
98
+ "attention_dropout": 0.0,
99
+ "bad_words_ids": null,
100
+ "begin_suppress_tokens": null,
101
+ "bos_token_id": null,
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_sample": false,
107
+ "dropout": 0.0,
108
+ "early_stopping": false,
109
+ "encoder_no_repeat_ngram_size": 0,
110
+ "eos_token_id": null,
111
+ "exponential_decay_length_penalty": null,
112
+ "finetuning_task": null,
113
+ "forced_bos_token_id": null,
114
+ "forced_eos_token_id": null,
115
+ "hidden_act": "gelu",
116
+ "hidden_size": 768,
117
+ "id2label": {
118
+ "0": "LABEL_0",
119
+ "1": "LABEL_1"
120
+ },
121
+ "image_size": 384,
122
+ "initializer_factor": 1.0,
123
+ "initializer_range": 0.02,
124
+ "intermediate_size": 3072,
125
+ "is_decoder": false,
126
+ "is_encoder_decoder": false,
127
+ "label2id": {
128
+ "LABEL_0": 0,
129
+ "LABEL_1": 1
130
+ },
131
+ "layer_norm_eps": 1e-05,
132
+ "length_penalty": 1.0,
133
+ "max_length": 20,
134
+ "min_length": 0,
135
+ "model_type": "blip_vision_model",
136
+ "no_repeat_ngram_size": 0,
137
+ "num_attention_heads": 12,
138
+ "num_beam_groups": 1,
139
+ "num_beams": 1,
140
+ "num_channels": 3,
141
+ "num_hidden_layers": 12,
142
+ "num_return_sequences": 1,
143
+ "output_attentions": false,
144
+ "output_hidden_states": false,
145
+ "output_scores": false,
146
+ "pad_token_id": null,
147
+ "patch_size": 16,
148
+ "prefix": null,
149
+ "problem_type": null,
150
+ "projection_dim": 512,
151
+ "pruned_heads": {},
152
+ "remove_invalid_values": false,
153
+ "repetition_penalty": 1.0,
154
+ "return_dict": true,
155
+ "return_dict_in_generate": false,
156
+ "sep_token_id": null,
157
+ "suppress_tokens": null,
158
+ "task_specific_params": null,
159
+ "temperature": 1.0,
160
+ "tf_legacy_loss": false,
161
+ "tie_encoder_decoder": false,
162
+ "tie_word_embeddings": true,
163
+ "tokenizer_class": null,
164
+ "top_k": 50,
165
+ "top_p": 1.0,
166
+ "torch_dtype": null,
167
+ "torchscript": false,
168
+ "transformers_version": "4.30.1",
169
+ "typical_p": 1.0,
170
+ "use_bfloat16": false
171
+ }
172
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26455cfd3890b83c2baa870e7a75dbe82ba7bb722a5dc7aba562c91c34287fc8
3
+ size 989827950
runs/Jun06_04-04-49_75fada0359be/events.out.tfevents.1717646848.75fada0359be.174.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55f81582a6bceceb98d162433e627f66bc2bc2a92e2eb47998e74f463cd9564d
3
+ size 80708
runs/Jun06_04-17-39_75fada0359be/events.out.tfevents.1717647469.75fada0359be.174.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27357069ee7727fca6a4c3c1d312150e605ed3ec3bda443f8326e9b6759d6c2e
3
+ size 8151
runs/Jun06_04-23-04_75fada0359be/events.out.tfevents.1717647796.75fada0359be.174.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19a09cc8579fa873fc12476b86ddedf2c95e0f531f4a63421a07debae5319aa1
3
+ size 88781
runs/Jun06_04-53-09_75fada0359be/events.out.tfevents.1717649654.75fada0359be.174.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db3a93ad3396048ce4ad6c23c72be232e634a01eb2f33960b1b17ee9736e5216
3
+ size 24277
runs/Jun06_04-56-09_75fada0359be/events.out.tfevents.1717649773.75fada0359be.174.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4f906521d00aeba1b3fc0d1e54d18b75965b60c9faebd8654d7a0a59ac82cc
3
+ size 8305
runs/Jun06_05-12-26_75fada0359be/events.out.tfevents.1717650761.75fada0359be.174.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe42f19c8d515c352b9fa9c1b831cfc3083928a5402e1dd6041393be4a7007a6
3
+ size 9436
runs/Jun06_05-27-35_75fada0359be/events.out.tfevents.1717651670.75fada0359be.174.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5165296963d44bac13531bc7057f88bf29c1cb33b943ec622264996f29c1cf5
3
+ size 12577
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff0e77902feab830196c8ef9b2bea6dd1b3c7f92be79a890af83d3c17e4b3202
3
+ size 4472