Hugging Face's logo

ShynBui
/
Bartpho_spelling_correction

Text2Text Generation
Transformers
TensorBoard
Safetensors
mbart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ShynBui commited on
Commit
68cf494
•
1 Parent(s): 0a1de92

Training in progress, step 4000

Browse files
Files changed (5) hide show
  1. config.json +37 -37
  2. model.safetensors +1 -1
  3. special_tokens_map.json +15 -51
  4. tokenizer_config.json +55 -55
  5. training_args.bin +2 -2
config.json CHANGED
@@ -1,37 +1,37 @@
1
- {
2
- "_name_or_path": "ShynBui/Bartpho_spelling_correction",
3
- "activation_dropout": 0.0,
4
- "activation_function": "gelu",
5
- "architectures": [
6
- "MBartForConditionalGeneration"
7
- ],
8
- "attention_dropout": 0.0,
9
- "bos_token_id": 0,
10
- "classifier_dropout": 0.0,
11
- "d_model": 1024,
12
- "decoder_attention_heads": 16,
13
- "decoder_ffn_dim": 4096,
14
- "decoder_layerdrop": 0.0,
15
- "decoder_layers": 12,
16
- "decoder_start_token_id": 2,
17
- "dropout": 0.1,
18
- "encoder_attention_heads": 16,
19
- "encoder_ffn_dim": 4096,
20
- "encoder_layerdrop": 0.0,
21
- "encoder_layers": 12,
22
- "eos_token_id": 2,
23
- "forced_eos_token_id": 2,
24
- "gradient_checkpointing": false,
25
- "init_std": 0.02,
26
- "is_encoder_decoder": true,
27
- "max_position_embeddings": 1024,
28
- "model_type": "mbart",
29
- "num_hidden_layers": 12,
30
- "pad_token_id": 1,
31
- "scale_embedding": false,
32
- "tokenizer_class": "BartphoTokenizer",
33
- "torch_dtype": "float32",
34
- "transformers_version": "4.42.4",
35
- "use_cache": true,
36
- "vocab_size": 40030
37
- }
 
1
+ {
2
+ "_name_or_path": "vinai/bartpho-syllable",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "MBartForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 0,
10
+ "classifier_dropout": 0.0,
11
+ "d_model": 1024,
12
+ "decoder_attention_heads": 16,
13
+ "decoder_ffn_dim": 4096,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 12,
16
+ "decoder_start_token_id": 2,
17
+ "dropout": 0.1,
18
+ "encoder_attention_heads": 16,
19
+ "encoder_ffn_dim": 4096,
20
+ "encoder_layerdrop": 0.0,
21
+ "encoder_layers": 12,
22
+ "eos_token_id": 2,
23
+ "forced_eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "init_std": 0.02,
26
+ "is_encoder_decoder": true,
27
+ "max_position_embeddings": 1024,
28
+ "model_type": "mbart",
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 1,
31
+ "scale_embedding": false,
32
+ "tokenizer_class": "BartphoTokenizer",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.44.2",
35
+ "use_cache": true,
36
+ "vocab_size": 40030
37
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2553f480ebb41a211ddb3230f550e0d0c34eeafb0b29e9740e59224a8ec44b2d
3
  size 1583480280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5a9b0ec141886572d025d675a3418aaba132514bb1aa4c35769fa11658b1c9e
3
  size 1583480280
special_tokens_map.json CHANGED
@@ -1,51 +1,15 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": true,
26
- "normalized": true,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "pad_token": {
31
- "content": "<pad>",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "</s>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "<unk>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
- }
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer_config.json CHANGED
@@ -1,55 +1,55 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "<pad>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "</s>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "<unk>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "40029": {
36
- "content": "<mask>",
37
- "lstrip": true,
38
- "normalized": true,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "bos_token": "<s>",
45
- "clean_up_tokenization_spaces": true,
46
- "cls_token": "<s>",
47
- "eos_token": "</s>",
48
- "mask_token": "<mask>",
49
- "model_max_length": 1000000000000000019884624838656,
50
- "pad_token": "<pad>",
51
- "sep_token": "</s>",
52
- "sp_model_kwargs": {},
53
- "tokenizer_class": "BartphoTokenizer",
54
- "unk_token": "<unk>"
55
- }
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "40029": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "BartphoTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9edaa30ac812c9ab80cbe669d04a212b3959873ab6d6477d9501a8fd9f49f0fb
3
- size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c4b544ae529b674fc21fd259d4ddd65f2a16657474e3fc05ec15c0c13b19ade
3
+ size 5368