lysandre HF staff Wauplin HF staff commited on
Commit
d94f213
1 Parent(s): 3391fef

Add `eos_token` to the tokenizer config. (#17)

Browse files

- Add `eos_token` to the tokenizer config. (58feb13af624846db7c9cb1c5c03498e5e49daef)
- Update tokenizer_config.json (64490687ea7285075e66616b8dd628b8d93d7fda)


Co-authored-by: Lucain Pouget <[email protected]>

Files changed (1) hide show
  1. tokenizer_config.json +21 -2
tokenizer_config.json CHANGED
@@ -1,4 +1,23 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "model_max_length": 1024,
3
- "chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}"
4
- }
 
 
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
16
+ "clean_up_tokenization_spaces": true,
17
+ "eos_token": "<|endoftext|>",
18
+ "errors": "replace",
19
  "model_max_length": 1024,
20
+ "pad_token": null,
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }