Skip to content

Conversation

@bkb2135
Copy link
Collaborator

@bkb2135 bkb2135 commented Feb 20, 2025

Changes

Copy link
Collaborator

@dbobrenko dbobrenko left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

richwardle and others added 29 commits March 3, 2025 13:19
…ute-error

Add Await To Inference Reward Model
Changes:
  - Fix error when `past_websites.csv` exists but empty.
  - Fix wrong pydantic models types, resulting in failed to validate pydantic model.
  - Remove AutoAWQ workaround, by switching to PR with `setup.py` fix to install it via poetry.
  - Allow floating point precision for max VRAM allowed.
Separate Prompting, Remove TTI Endpoint, Add Json Flag
- Hotfix HF model initialization by respecting specified model ID.
- Use specified model device instead of cuda:0.
- Decouple HF model from settings.
- Remove redundant params passed to HF.
- Fix typings.
Changes:
  - Hotfix HF model initialization by respecting specified model ID, 
    caused by suppressing error with `**kwargs` in model constructor. 
  - Use specified model device instead of hard-coded `cuda:0`.
  - Decouple HF model from settings.
  - Remove redundant params passed to HF.
  - Fix typings.
…o-work-with-langflow-traffic

Allow langflow arguments to be properly parsed by completion endpoint
@bkb2135 bkb2135 merged commit 9f90feb into main Mar 12, 2025
1 check passed
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.

6 participants