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.

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

[Feature]: Add Top K as a backend parameter #1105

Closed
2 tasks done
anders-swanson opened this issue May 9, 2024 · 0 comments · Fixed by #1110
Closed
2 tasks done

[Feature]: Add Top K as a backend parameter #1105

anders-swanson opened this issue May 9, 2024 · 0 comments · Fixed by #1110

Comments

@anders-swanson
Copy link
Contributor

Checklist

  • I've searched for similar issues and couldn't find anything matching
  • I've discussed this feature request in the K8sGPT Slack and got positive feedback

Is this feature request related to a problem?

No

Problem Description

Top K is a common parameter for models. This parameter should be added to k8sgpt, and configurable for any backends which have models that support Top K.

Solution Description

  1. Add Top K as a new backend parameter
  2. For any backends that can utilize Top K, update the outbound requests to use Top K.

Benefits

Users gain additional configuration over the backend model by utilizing the Top K parameter.

Potential Drawbacks

No response

Additional Information

No response
VaibhavMalik4187 added a commit to VaibhavMalik4187/k8sgpt that referenced this issue May 11, 2024
@VaibhavMalik4187
feat: introduce the Top K parameter in AI configs
dadd3f6 
This commit adds Top-K sampling, a feature that allows users to control
the randomness of the generated text by specifying the number of most
probable next words considered by the model. This enhances user control
and potentially improves the quality of the generated outputs.

Fixes: k8sgpt-ai#1105

Signed-off-by: VaibhavMalik4187 <[email protected]>
@VaibhavMalik4187 VaibhavMalik4187 mentioned this issue May 11, 2024
Merged
4 tasks
VaibhavMalik4187 added a commit to VaibhavMalik4187/k8sgpt that referenced this issue May 11, 2024
@VaibhavMalik4187
feat: implement Top-K sampling for improved user control
45bec75 
This commit adds Top-K sampling, a feature that allows users to control
the randomness of the generated text by specifying the number of most
probable next words considered by the model. This enhances user control
and potentially improves the quality of the generated outputs.

Fixes: k8sgpt-ai#1105

Signed-off-by: VaibhavMalik4187 <[email protected]>
AlexsJones added a commit that referenced this issue May 16, 2024
@VaibhavMalik4187 @AlexsJones
feat: implement Top-K sampling for improved user control (#1110)
eda5231 
This commit adds Top-K sampling, a feature that allows users to control
the randomness of the generated text by specifying the number of most
probable next words considered by the model. This enhances user control
and potentially improves the quality of the generated outputs.

Fixes: #1105

Signed-off-by: VaibhavMalik4187 <[email protected]>
Co-authored-by: Alex Jones <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
Backlog
Status: Done
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

feat: implement Top-K sampling for improved user control VaibhavMalik4187/k8sgpt
1 participant
@anders-swanson