Hooshaai
/

AsyncTensorRLHF

Reinforcement Learning

Model card Files Files and versions

AsyncTensorRLHF / src /reward /__init__.py

tahamajs's picture

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

e791b16 verified 2 months ago

Raw History Blame Contribute Delete

29 Bytes

	# Reward package initializer