arcee-ai / mergekit

Tools for merging pretrained large language models.
GNU Lesser General Public License v3.0
4.88k stars 446 forks source link

Specify chat template for output model #367

Closed cg123 closed 4 months ago

cg123 commented 4 months ago

Adds a chat_template field to merge configs, which can either be a Jinja template string or one of chatml, llama3, alpaca, mistral. Also supports auto which will try to select the most common template among the input models.