Skip to content

Conversation

@HenriqueAssumpcao
Copy link
Contributor

This PR allows users to identify which LLM in the ensemble was used to generate a given program. We achieve this by a new attribute to the Program class called model_id, which stores the index of the LLMEnsemble model used to generate the program. Some of the generate methods from the LLMEnsemble class now also return the index of the sampled model. Some minor changes to unit tests were needed. This solves #381.

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