nxquang-al
commited on
Commit
•
fbbf7f5
1
Parent(s):
4199567
Epoch 5: Val_WER: 0.5684 - Val_BLEU: 0.3121
Browse files- config.json +26 -0
- generation_config.json +7 -0
- preprocessor_config.json +25 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Salesforce/blip-image-captioning-base",
|
3 |
+
"architectures": [
|
4 |
+
"BlipForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"image_text_hidden_size": 256,
|
7 |
+
"initializer_factor": 1.0,
|
8 |
+
"initializer_range": 0.02,
|
9 |
+
"logit_scale_init_value": 2.6592,
|
10 |
+
"model_type": "blip",
|
11 |
+
"projection_dim": 512,
|
12 |
+
"text_config": {
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"model_type": "blip_text_model",
|
15 |
+
"num_attention_heads": 12
|
16 |
+
},
|
17 |
+
"torch_dtype": "float32",
|
18 |
+
"transformers_version": "4.33.0.dev0",
|
19 |
+
"vision_config": {
|
20 |
+
"dropout": 0.0,
|
21 |
+
"initializer_factor": 1.0,
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"model_type": "blip_vision_model",
|
24 |
+
"num_channels": 3
|
25 |
+
}
|
26 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 30522,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.33.0.dev0"
|
7 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"is_vqa": false,
|
18 |
+
"processor_class": "BlipProcessor",
|
19 |
+
"resample": 3,
|
20 |
+
"rescale_factor": 0.00392156862745098,
|
21 |
+
"size": {
|
22 |
+
"height": 384,
|
23 |
+
"width": 384
|
24 |
+
}
|
25 |
+
}
|
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 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": true,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_input_names": [
|
8 |
+
"input_ids",
|
9 |
+
"attention_mask"
|
10 |
+
],
|
11 |
+
"model_max_length": 512,
|
12 |
+
"never_split": null,
|
13 |
+
"pad_token": "[PAD]",
|
14 |
+
"processor_class": "BlipProcessor",
|
15 |
+
"sep_token": "[SEP]",
|
16 |
+
"strip_accents": null,
|
17 |
+
"tokenize_chinese_chars": true,
|
18 |
+
"tokenizer_class": "BertTokenizer",
|
19 |
+
"trust_remote_code": false,
|
20 |
+
"unk_token": "[UNK]"
|
21 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|