8000 Update datasets requirement from <5,>=4.0 to >=4.0,<6 by dependabot[bot] · Pull Request #110 · DaoyuanLi2816/mini-verl · GitHub
[go: up one dir, main page]
Skip to content

Update datasets requirement from <5,>=4.0 to >=4.0,<6 #110

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

Closed
dependabot wants to merge 1 commit into from
Closed

Update datasets requirement from <5,>=4.0 to >=4.0,<6 #110

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,7 @@ train = [
cuda = ["bitsandbytes>=0.43; platform_system != 'Darwin'"]
dpo = [
"trl==1.8.0",
"datasets>=4.0,<5",
"datasets>=4.0,<6",
]
# numpy is what the official safetensors reader needs for framework="np". Without
# it the adapter payload can still be validated structurally, but
Expand All @@ -79,7 +79,7 @@ rollout-vllm = [
# judge models or a network client. The judge models themselves are ordinary
# transformers checkpoints, so [train] supplies the runtime for them.
alignment-benchmarks = [
"datasets>=4.0,<5",
"datasets>=4.0,<6",
# IFEval's language:response_language instruction cannot be verified without
# language identification. Absent it, that instruction reports
# not_applicable rather than being guessed or scored zero.
Expand Down
0