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

Test prefill prompt with Anthropic models #28

Open
nkkko opened this issue Oct 1, 2024 · 3 comments
Open

Test prefill prompt with Anthropic models #28

nkkko opened this issue Oct 1, 2024 · 3 comments

Comments

@nkkko
Copy link
Member

nkkko commented Oct 1, 2024

When using models that enable pre-filling, like Anthropic, we should try pre-filling the outputs:
https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/prefill-claudes-response

This needs #10 to be solved first.

@nkkko
Copy link
Member Author

nkkko commented Oct 9, 2024

/bounty $20

Copy link

algora-pbc bot commented Oct 9, 2024

💎 $20 bounty • Daytona

Steps to solve:

  1. Start working: Comment /attempt #28 with your implementation plan
  2. Submit work: Create a pull request including /claim #28 in the PR body to claim the bounty
  3. Receive payment: 100% of the bounty is received 2-5 days post-reward. Make sure you are eligible for payouts

If no one is assigned to the issue, feel free to tackle it, without confirmation from us, after registering your attempt. In the event that multiple PRs are made from different people, we will generally accept those with the cleanest code.

Please respect others by working on PRs that you are allowed to submit attempts to.

e.g. If you reached the limit of active attempts, please wait for the ability to do so before submitting a new PR.

If you can not submit an attempt, you will not receive your payout.

Thank you for contributing to daytonaio/devcontainer-generator!

Add a bountyShare on socials

Attempt Started (GMT+0) Solution
🟢 @madman024 Oct 10, 2024, 7:51:22 PM WIP

@madman024
Copy link

madman024 commented Oct 10, 2024

/attempt #28
Hey, I've got a plan for implementing prefill support across our LLM providers, focusing on Anthropic's Claude models initially. Here's how we can tackle this:
Prefill Support Implementation Plan

Adding prefill support will give us way more control over our devcontainer.json generation. It'll help us:
Get more consistent, structured outputs
Skip unnecessary preambles
Guide the model to follow our exact formatting needs

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants