NeuraCraft commited on
Commit
84d4bfe
·
verified ·
1 Parent(s): bcf5d75

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +16 -2
  2. tokenizer_config.json +7 -0
tokenizer.json CHANGED
@@ -1,7 +1,21 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 100256,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 512
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 100257,
16
+ "pad_type_id": 0,
17
+ "pad_token": "<|endoftext|>"
18
+ },
19
  "added_tokens": [
20
  {
21
  "id": 100256,
tokenizer_config.json CHANGED
@@ -197,8 +197,15 @@
197
  "clean_up_tokenization_spaces": true,
198
  "eos_token": "<|endoftext|>",
199
  "extra_special_tokens": {},
 
200
  "model_max_length": 1000000000000000019884624838656,
 
201
  "pad_token": "<|endoftext|>",
 
 
 
202
  "tokenizer_class": "GPT2Tokenizer",
 
 
203
  "unk_token": "<|endoftext|>"
204
  }
 
197
  "clean_up_tokenization_spaces": true,
198
  "eos_token": "<|endoftext|>",
199
  "extra_special_tokens": {},
200
+ "max_length": 512,
201
  "model_max_length": 1000000000000000019884624838656,
202
+ "pad_to_multiple_of": null,
203
  "pad_token": "<|endoftext|>",
204
+ "pad_token_type_id": 0,
205
+ "padding_side": "right",
206
+ "stride": 0,
207
  "tokenizer_class": "GPT2Tokenizer",
208
+ "truncation_side": "right",
209
+ "truncation_strategy": "longest_first",
210
  "unk_token": "<|endoftext|>"
211
  }