Skip to content

add llama2 model options #44

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.

Sign up for GitHub

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

Jump to bottom
Closed
wants to merge 7 commits into from
Closed

add llama2 model options #44

wants to merge 7 commits into from

Conversation

davidsbailey
Copy link
Member

@davidsbailey davidsbailey commented Jan 30, 2024 •
edited
Loading

depends on #43

add llama2 model

this PR adds the ability to select a llama2 model for evaluation. currently, llama2 gives an evaluation of all requested learning goals in JSON format, but accuracy is low (near random).

notable in this PR:

  • wrap system prompt text in [INST]...[/INST] tags
  • change AI response format from TSV to JSON

to try next:

  • provide examples

@davidsbailey davidsbailey marked this pull request as draft January 30, 2024 01:12
Base automatically changed from aws-bedrock-llama to main February 1, 2024 21:37
@davidsbailey
Copy link
Member Author

closing in favor of #54

@davidsbailey davidsbailey deleted the add-llama2-model-option branch February 16, 2024 19:00
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@davidsbailey