Hugging Face's logo

chamdentimem
/
vietnamese-correction-nlp

Text2Text Generation
Transformers
TensorBoard
Safetensors
mbart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
chamdentimem commited on
Commit
6639b59
•
1 Parent(s): 4c2b3e6

Training in progress, step 500

Browse files
Files changed (11) hide show
  1. config.json +37 -0
  2. dict.txt +0 -0
  3. model.safetensors +3 -0
  4. runs/May12_17-48-38_a0becc0c8017/events.out.tfevents.1715536158.a0becc0c8017.1097.0 +3 -0
  5. runs/May12_18-11-04_a0becc0c8017/events.out.tfevents.1715537474.a0becc0c8017.1097.1 +3 -0
  6. runs/May12_18-12-11_a0becc0c8017/events.out.tfevents.1715537540.a0becc0c8017.1097.2 +3 -0
  7. runs/May12_18-18-18_a0becc0c8017/events.out.tfevents.1715537899.a0becc0c8017.12155.0 +3 -0
  8. sentencepiece.bpe.model +3 -0
  9. special_tokens_map.json +15 -0
  10. tokenizer_config.json +55 -0
  11. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "4.40.2",
35
+ "use_cache": true,
36
+ "vocab_size": 40030
37
+ }
dict.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72418b42ed84a73b723dedeec15ecbe6ce76a1401cdb133e81cae8752b080005
3
+ size 1583480280
runs/May12_17-48-38_a0becc0c8017/events.out.tfevents.1715536158.a0becc0c8017.1097.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c1e20538b4dd082de54534630354a62a198d1f1437e0f109c203bdac4b58102
3
+ size 5186
runs/May12_18-11-04_a0becc0c8017/events.out.tfevents.1715537474.a0becc0c8017.1097.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e32d8cdd8e000884c10ad1cc6a5b8aaca47e8357d126006c1b1cb40be12178e6
3
+ size 5186
runs/May12_18-12-11_a0becc0c8017/events.out.tfevents.1715537540.a0becc0c8017.1097.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:181a6dd922b4e71fb54334d4a6185d2408d5e01338fe66e3e3a578c87579b14f
3
+ size 5183
runs/May12_18-18-18_a0becc0c8017/events.out.tfevents.1715537899.a0becc0c8017.12155.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f6a8a4916bbe00332c06077a8700643632f601ad0ae38eff97d0c877c879317
3
+ size 5183
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9600faa6b7b37dc108ff9debb3b379c45580791066d3bde2b4489582ea358f91
3
+ size 5176