Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature LLM based Curation #10

Merged
merged 6 commits into from
Sep 26, 2024
Merged

Conversation

sumanthprabhu
Copy link
Owner

  • Implemented LLM based curation using self-ensembling to compute reliability scores for text generation usecases
  • Implemented util functions to perform batch inference using LLMs
  • Added corresponding tests
  • Updated the dependencies in pyproject.toml
  • Bumped the version from 0.1.3 to 0.2.0

- Implemented LLM based curation using self-ensembling to compute reliability scores for text generation usecases
- Implemented util functions to perform batch inference using LLMs
- Added corresponding tests
- Updated the dependencies in pyproject.toml
- Bumped the version from 0.1.3 to 0.2.0
- Implemented `set_seed` in base.py to ensure reproducible results
- Implemented `set_seed` for LLM Utils to ensure reproducibility.
- Added corresponding unit tests
- Code refactoring for LLM Util functions
- Added test to verify that all imports work correctly
- Refactored `run` method to aggregate parameters related computing confidence scores into a single dictionary `scoring_params`
- Refactored corresponding tests
@sumanthprabhu sumanthprabhu merged commit f6a96b3 into main Sep 26, 2024
0 of 2 checks 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.

1 participant