Xenova HF staff commited on
Commit
98d53b8
·
verified ·
1 Parent(s): be25e91

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 +34 -33
tokenizer_config.json CHANGED
@@ -1,34 +1,35 @@
1
  {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "bos_token": {
5
- "__type": "AddedToken",
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "eos_token": {
13
- "__type": "AddedToken",
14
- "content": "<|endoftext|>",
15
- "lstrip": false,
16
- "normalized": true,
17
- "rstrip": false,
18
- "single_word": false
19
- },
20
- "errors": "replace",
21
- "model_max_length": 1024,
22
- "name_or_path": "microsoft/DialoGPT-medium",
23
- "pad_token": null,
24
- "special_tokens_map_file": null,
25
- "tokenizer_class": "GPT2Tokenizer",
26
- "unk_token": {
27
- "__type": "AddedToken",
28
- "content": "<|endoftext|>",
29
- "lstrip": false,
30
- "normalized": true,
31
- "rstrip": false,
32
- "single_word": false
33
- }
34
- }
 
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 1024,
22
+ "name_or_path": "microsoft/DialoGPT-medium",
23
+ "pad_token": null,
24
+ "special_tokens_map_file": null,
25
+ "tokenizer_class": "GPT2Tokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}"
35
+ }