crarojasca commited on
Commit
e031632
·
1 Parent(s): f2e0c49

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +2 -16
  2. tokenizer_config.json +2 -3
tokenizer.json CHANGED
@@ -1,21 +1,7 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 256,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 256
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 1,
16
- "pad_type_id": 0,
17
- "pad_token": "<pad>"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
tokenizer_config.json CHANGED
@@ -2,14 +2,13 @@
2
  "add_prefix_space": false,
3
  "bos_token": "<s>",
4
  "cls_token": "<s>",
 
5
  "eos_token": "</s>",
6
  "errors": "replace",
7
  "mask_token": "<mask>",
8
  "model_max_length": 512,
9
- "name_or_path": "model/waterloo_cards_SEED_3782740472/best-epoch",
10
  "pad_token": "<pad>",
11
- "padding": true,
12
- "return_tensors": "tf",
13
  "sep_token": "</s>",
14
  "special_tokens_map_file": null,
15
  "tokenizer_class": "RobertaTokenizer",
 
2
  "add_prefix_space": false,
3
  "bos_token": "<s>",
4
  "cls_token": "<s>",
5
+ "do_lower_case": false,
6
  "eos_token": "</s>",
7
  "errors": "replace",
8
  "mask_token": "<mask>",
9
  "model_max_length": 512,
10
+ "name_or_path": "model/waterlo_cards_cardsScript_SEED_3782740472/best_model/",
11
  "pad_token": "<pad>",
 
 
12
  "sep_token": "</s>",
13
  "special_tokens_map_file": null,
14
  "tokenizer_class": "RobertaTokenizer",