Text Generation
Transformers
Safetensors
gpt2
text-generation-inference
Inference Endpoints
4-bit precision
gptq
Xenova HF staff commited on
Commit
38adb1d
·
verified ·
1 Parent(s): fd6a00c

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 +3 -2
tokenizer_config.json CHANGED
@@ -45,5 +45,6 @@
45
  "sp_model_kwargs": {},
46
  "tokenizer_class": "GPTSw3Tokenizer",
47
  "truncation_side": "left",
48
- "unk_token": "<unk>"
49
- }
 
 
45
  "sp_model_kwargs": {},
46
  "tokenizer_class": "GPTSw3Tokenizer",
47
  "truncation_side": "left",
48
+ "unk_token": "<unk>",
49
+ "chat_template": "{{ eos_token }}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content']}}{% else %}{{ 'Bot: ' + message['content']}}{% endif %}{{ message['text'] }}{{ bos_token }}{% endfor %}Bot:"
50
+ }