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

Align parameters for "max_token, repetition_penalty,presence_penalty,frequency_penalty" #608

Merged
merged 33 commits into from
Sep 18, 2024

Conversation

XinyaoWa
Copy link
Collaborator

@XinyaoWa XinyaoWa commented Sep 4, 2024

Description

  1. Support and clarify the usage for frequency_penalty/presence_penalty/repetition_penalty
  1. Align to max_tokens for LLM
  • Comps: LLMs use max_tokens, others use max_new_tokens
  • Examples(keep unchanged): Most use max_tokens
  1. Fix langchain version issue for faq/vllm

Issues

opea-project/GenAIExamples#673

Signed-off-by: Xinyao Wang <[email protected]>
Signed-off-by: Xinyao Wang <[email protected]>
Copy link

codecov bot commented Sep 4, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Files with missing lines Coverage Δ
comps/cores/mega/gateway.py 35.32% <ø> (ø)
comps/cores/proto/api_protocol.py 96.00% <100.00%> (+0.01%) ⬆️
comps/cores/proto/docarray.py 99.28% <100.00%> (+0.03%) ⬆️

@lvliang-intel
Copy link
Collaborator

@XinyaoWa,
please check the CI issues.

@chensuyue chensuyue modified the milestones: v0.9, v1.0 Sep 5, 2024
@chensuyue chensuyue removed this from the v1.0 milestone Sep 11, 2024
@XinyaoWa XinyaoWa changed the title Align parameters for "max_new_tokens" and "repetition_penalty" Align parameters for "max_new_token, repetition_penalty,presence_penalty,frequency_penalty" Sep 13, 2024
Signed-off-by: Xinyao Wang <[email protected]>
Signed-off-by: Xinyao Wang <[email protected]>
Signed-off-by: Xinyao Wang <[email protected]>
Signed-off-by: Xinyao Wang <[email protected]>
Signed-off-by: Xinyao Wang <[email protected]>
@lkk12014402
Copy link
Collaborator

LGTM

@XinyaoWa XinyaoWa mentioned this pull request Sep 18, 2024
1 task
@XinyaoWa XinyaoWa changed the title Align parameters for "max_new_token, repetition_penalty,presence_penalty,frequency_penalty" Align parameters for "max_token, repetition_penalty,presence_penalty,frequency_penalty" Sep 18, 2024
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.

7 participants