Xenova HF staff commited on
Commit
8a9c7f9
1 Parent(s): 2b9c48d

Add default chat template to tokenizer_config.json

Browse files

[Automated] This PR adds the default chat template to the tokenizer config, allowing the model to be used with the new conversational widget (see [PR](https://github.com/huggingface/huggingface.js/pull/457)).

If the default is not appropriate for your model, please set `tokenizer.chat_template` to an appropriate template. See https://huggingface.co/docs/transformers/main/chat_templating for more information.

Files changed (1) hide show
  1. tokenizer_config.json +37 -1
tokenizer_config.json CHANGED
@@ -1 +1,37 @@
1
- {"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "pad_token": "<|endoftext|>", "cls_token": "<|cls|>", "sep_token": "<|sep|>", "special_tokens_map_file": null, "full_tokenizer_file": null, "tokenizer_file": "/home/af1tang/convogym/checkpoint/model/tokenizer.json", "name_or_path": "/home/af1tang/convogym/checkpoint/model/", "tokenizer_class": "GPT2Tokenizer"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "errors": "replace",
3
+ "unk_token": {
4
+ "content": "<|endoftext|>",
5
+ "single_word": false,
6
+ "lstrip": false,
7
+ "rstrip": false,
8
+ "normalized": true,
9
+ "__type": "AddedToken"
10
+ },
11
+ "bos_token": {
12
+ "content": "<|endoftext|>",
13
+ "single_word": false,
14
+ "lstrip": false,
15
+ "rstrip": false,
16
+ "normalized": true,
17
+ "__type": "AddedToken"
18
+ },
19
+ "eos_token": {
20
+ "content": "<|endoftext|>",
21
+ "single_word": false,
22
+ "lstrip": false,
23
+ "rstrip": false,
24
+ "normalized": true,
25
+ "__type": "AddedToken"
26
+ },
27
+ "add_prefix_space": false,
28
+ "pad_token": "<|endoftext|>",
29
+ "cls_token": "<|cls|>",
30
+ "sep_token": "<|sep|>",
31
+ "special_tokens_map_file": null,
32
+ "full_tokenizer_file": null,
33
+ "tokenizer_file": "/home/af1tang/convogym/checkpoint/model/tokenizer.json",
34
+ "name_or_path": "/home/af1tang/convogym/checkpoint/model/",
35
+ "tokenizer_class": "GPT2Tokenizer",
36
+ "chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}"
37
+ }