Validate server params & fix logit bias bug (#731)

* Bug fix in logit bias

* Add parameter validations

* Fix typo

* Update docstrings to match MLX styling

* Black style + fix a validation bug
This commit is contained in:
Karim Elmaaroufi
2024-04-30 07:27:40 -07:00
committed by GitHub
parent 7c0962f4e2
commit 4bf2eb17f2
3 changed files with 55 additions and 8 deletions

View File

@@ -71,3 +71,6 @@ curl localhost:8080/v1/chat/completions \
- `repetition_context_size`: (Optional) The size of the context window for
applying repetition penalty. Defaults to `20`.
- `logit_bias`: (Optional) A dictionary mapping token IDs to their bias
values. Defaults to `None`.