ramdhanfirdaus commited on
Commit
627aa1f
1 Parent(s): eb4c0f1

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -12,12 +12,5 @@
12
  ">>SUFFIX<<",
13
  ">>MIDDLE<<"
14
  ],
15
- "eos_token": {
16
- "content": "<|endoftext|>",
17
- "lstrip": false,
18
- "normalized": false,
19
- "rstrip": false,
20
- "single_word": false
21
- },
22
- "pad_token": "<|endoftext|>"
23
  }
 
12
  ">>SUFFIX<<",
13
  ">>MIDDLE<<"
14
  ],
15
+ "eos_token": "<|endoftext|>"
 
 
 
 
 
 
 
16
  }
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
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
@@ -113,15 +113,10 @@
113
  ],
114
  "clean_up_tokenization_spaces": true,
115
  "eos_token": "<|endoftext|>",
116
- "max_length": 512,
117
  "model_input_names": [
118
  "input_ids",
119
  "attention_mask"
120
  ],
121
  "model_max_length": 2048,
122
- "pad_token": "<|endoftext|>",
123
- "stride": 0,
124
- "tokenizer_class": "PreTrainedTokenizerFast",
125
- "truncation_side": "right",
126
- "truncation_strategy": "longest_first"
127
  }
 
113
  ],
114
  "clean_up_tokenization_spaces": true,
115
  "eos_token": "<|endoftext|>",
 
116
  "model_input_names": [
117
  "input_ids",
118
  "attention_mask"
119
  ],
120
  "model_max_length": 2048,
121
+ "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
 
122
  }