latishab commited on
Commit
2ae8c32
·
verified ·
1 Parent(s): dddd6ef

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +7 -4
  2. tokenizer_config.json +4 -0
tokenizer.json CHANGED
@@ -1,10 +1,13 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": {
5
- "strategy": {
6
- "Fixed": 256
7
- },
8
  "direction": "Right",
9
  "pad_to_multiple_of": null,
10
  "pad_id": 2,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 128,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": {
10
+ "strategy": "BatchLongest",
 
 
11
  "direction": "Right",
12
  "pad_to_multiple_of": null,
13
  "pad_id": 2,
tokenizer_config.json CHANGED
@@ -147,8 +147,12 @@
147
  "clean_up_tokenization_spaces": false,
148
  "eos_token": "<|im_end|>",
149
  "extra_special_tokens": {},
 
150
  "model_max_length": 8192,
 
151
  "pad_token": "<|im_end|>",
 
 
152
  "tokenizer_class": "GPT2Tokenizer",
153
  "unk_token": "<|endoftext|>",
154
  "vocab_size": 49152
 
147
  "clean_up_tokenization_spaces": false,
148
  "eos_token": "<|im_end|>",
149
  "extra_special_tokens": {},
150
+ "max_length": 256,
151
  "model_max_length": 8192,
152
+ "pad_to_multiple_of": null,
153
  "pad_token": "<|im_end|>",
154
+ "pad_token_type_id": 0,
155
+ "padding_side": "right",
156
  "tokenizer_class": "GPT2Tokenizer",
157
  "unk_token": "<|endoftext|>",
158
  "vocab_size": 49152