Hugging Face's logo

Tung177
/
sentence-splitting

Text2Text Generation
Transformers
TensorBoard
Safetensors
mbart
Inference Endpoints
Model card Files Metrics Community
Tung177 commited on
Commit
32d2615
•
1 Parent(s): cdac515

Training in progress, step 1000

Browse files
Files changed (8) hide show
  1. config.json +1 -1
  2. dict.txt +0 -0
  3. model.safetensors +1 -1
  4. runs/Nov15_09-46-54_43e2a7e098e6/events.out.tfevents.1700041623.43e2a7e098e6.39690.0 +3 -0
  5. sentencepiece.bpe.model +3 -0
  6. special_tokens_map.json +15 -0
  7. tokenizer_config.json +55 -0
  8. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "vinai/bartpho-syllable",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "architectures": [
 
1
  {
2
+ "_name_or_path": "Tung177/sentence-splitting",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "architectures": [
dict.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78145131d36e4b2467150e92a097cec08fc7c4dcb3224921267472b5fc0589cf
3
  size 1583480280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:976c254a22caa4bd75723c6713100c8b1a712eb98c9d153a86648ce7311020c6
3
  size 1583480280
runs/Nov15_09-46-54_43e2a7e098e6/events.out.tfevents.1700041623.43e2a7e098e6.39690.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:067205b757d3b72083c3e4771ac3f6e7e86956fe6e7dc248b33ef548b7906504
3
+ size 5272
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": 1024,
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:f315121dc2b5b9937756f1d44b8176f31d5c40838fe6e08b5809ae1c2b292763
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34a4e9d5cf38cd53be9786596e206485b2a41bc2e4d40b4935804e381548c61f
3
  size 4728