w95 commited on
Commit
56e5710
1 Parent(s): c1fce73

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -9,6 +9,6 @@
9
  ],
10
  "bos_token": "<s>",
11
  "eos_token": "</s>",
12
- "pad_token": "</s>",
13
  "unk_token": "<unk>"
14
  }
 
9
  ],
10
  "bos_token": "<s>",
11
  "eos_token": "</s>",
12
+ "pad_token": "[PAD]",
13
  "unk_token": "<unk>"
14
  }
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 1024,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
tokenizer_config.json CHANGED
@@ -62,7 +62,7 @@
62
  "eos_token": "</s>",
63
  "legacy": false,
64
  "model_max_length": 1000000000000000019884624838656,
65
- "pad_token": "</s>",
66
  "padding_side": "right",
67
  "sp_model_kwargs": {},
68
  "tokenizer_class": "LlamaTokenizer",
 
62
  "eos_token": "</s>",
63
  "legacy": false,
64
  "model_max_length": 1000000000000000019884624838656,
65
+ "pad_token": "[PAD]",
66
  "padding_side": "right",
67
  "sp_model_kwargs": {},
68
  "tokenizer_class": "LlamaTokenizer",