Skip to content

Automatically set chat format from gguf#1110

Merged
abetlen merged 4 commits intomainfrom
chat-format-from-gguf
Jan 29, 2024
Merged

Automatically set chat format from gguf#1110
abetlen merged 4 commits intomainfrom
chat-format-from-gguf

Conversation

@abetlen
Copy link
Copy Markdown
Owner

@abetlen abetlen commented Jan 19, 2024

Closes #1096

Okay so for now this is going to be the behaviour / priority of the automatic chat format detection

  1. Use provided chat_handler param
  2. Use provided chat_format param
  3. If model has a gguf chat_template try to string match it against known jinja2 templates and use the matching template's eos token
  4. If model has a gguf chat_template use eos_token for stop generation
  5. Use llama 2 chat format

@abetlen abetlen merged commit da003d8 into main Jan 29, 2024
@abetlen abetlen deleted the chat-format-from-gguf branch January 31, 2024 20:27
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Use chat_template from gguf metadata

1 participant