initialized with grpo

This commit is contained in:
Olivier D'Ancona 2025-05-18 13:41:01 -07:00
parent f052f14484
commit 0fbb112eec
4 changed files with 636 additions and 1 deletions

View file

@ -1 +1,8 @@
use uv :D
torch
transformers
vllm
pydantic
numpy
requests
tenacity
wandb