Hugging Face's logo

ssdatar
/
output

Text2Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ssdatar commited on
Commit
881c46a
•
1 Parent(s): bad8658

Training in progress, step 500

Browse files
Files changed (6) hide show
  1. pytorch_model.bin +2 -2
  2. special_tokens_map.json +28 -5
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +37 -10
  5. training_args.bin +1 -1
  6. vocab.json +0 -0
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:036a9a4ce48845195aaaf2081d97ca78d678a5626765721f9da8768324ebf096
3
- size 205317885
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:684a54f870cdb0f8a5ac13b49414ac4c165241316d747c29944d7838fc9a2cdb
3
+ size 501023389
special_tokens_map.json CHANGED
@@ -1,7 +1,30 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,13 +1,40 @@
1
  {
 
 
 
 
 
 
 
 
 
 
2
  "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_lower_case": true,
5
- "mask_token": "[MASK]",
6
- "model_max_length": 512,
7
- "pad_token": "[PAD]",
8
- "sep_token": "[SEP]",
9
- "strip_accents": null,
10
- "tokenize_chinese_chars": true,
11
- "tokenizer_class": "ElectraTokenizer",
12
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "</s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
  "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<pad>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "tokenizer_class": "GPT2Tokenizer",
32
+ "unk_token": {
33
+ "__type": "AddedToken",
34
+ "content": "</s>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:162f6ed50c35c56bdddef267617562a90741dbbd8d166fea2e8e82232ccc6cf8
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53313092d109a391e0898b0bee6844ea392965c8c5bf148cfbb0c514976d9e88
3
  size 4027
vocab.json CHANGED
The diff for this file is too large to render. See raw diff