PyPI page
Home page
Author:
Chenmien Tan, Simon Yu, Lanbo Lin, Ze Zhang, Yuanwu Xu, Chenhao Jiang, Tianyuan Yang, Sicong Xie, Guannan Zhang
Summary:
RL2: Ray Less Reinforcement Learning
Latest version:
0.0.2
Required dependencies:
flash-attn
|
hydra-core
|
liger_kernel
|
ninja
|
peft
|
ring-flash-attn
|
sglang
|
torch
|
torchdata
|
tqdm
|
transformers
|
wandb
Downloads last day:
6
Downloads last week:
12
Downloads last month:
22