Add default chat template to tokenizer_config.json
#2
by
Xenova
HF staff
- opened
[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).
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.
LGTM.
This model however did not gain anything on the benchmarks. But did not loose performance either.
So may be more benefitial to try the same merge with other finetunes.
nisten
changed pull request status to
merged