Hugging Face's logo

tahamajs
/
AsyncTensorRLHF

Reinforcement Learning
PyTorch
English
rlhf
ppo
grpo
m2po
vllm
async
cuda
tensor-native
Model card Files
xet
 Community
AsyncTensorRLHF / src /trainer /trainer_worker.py

Commit History

Initial release of AsyncTensorRLHF: High-Throughput Asynchronous RLHF with Tensor-Native Rewards
e791b16
verified

tahamajs commited on