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]: Implementation of DRY sampler. #574

Open
Abdulhanan535 opened this issue Aug 10, 2024 · 4 comments
Open

[Feature]: Implementation of DRY sampler. #574

Abdulhanan535 opened this issue Aug 10, 2024 · 4 comments

Comments

@Abdulhanan535
Copy link

🚀 The feature, motivation and pitch

Majority of the bots repeat sentences and due to that, it's annoying.

Implementing DRY sampler for Aphrodite Engine.

DRY is a sampler that forces the model to not repeat while mantaining the quality or even improving it, some of the backends have already support for this.

  • Text Gen webui
  • koboldai
  • llamaccp

Alternatives

No response

Additional context

No response

@81549361
Copy link

81549361 commented Aug 11, 2024

+1
LostRuins/koboldcpp#982

@AlpinDale
Copy link
Member

Might be interesting to add. I currently don't have the bandwidth to tackle this. I may have the time after the 0.5.4 release, but if someone else wants to take over for now, it should be quite easy:

  1. Add the parameters related to the DRY sampler here: https://github.com/PygmalionAI/aphrodite-engine/blob/rc_054/aphrodite/common/sampling_params.py

  2. Define the sampler's metadata here. e.g. the conditions for triggering it (could be a related sampler param being set to higher than 0, etc) and create the necessary tensors. Plenty of examples here so you won't be lost: https://github.com/PygmalionAI/aphrodite-engine/blob/rc_054/aphrodite/modeling/sampling_metadata.py

  3. Finally, implement the actual sampler logic here: https://github.com/PygmalionAI/aphrodite-engine/blob/rc_054/aphrodite/modeling/layers/sampler.py

Should be plenty of examples at each step from other samplers. Please make sure you contribute to the rc_054 branch, unless you're reading this in a few weeks and that branch is merged into main.

@Abdulhanan535
Copy link
Author

any chance for this?

@Abdulhanan535
Copy link
Author

like this
``

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

No branches or pull requests

3 participants