RHFS模型研究与强化学习

深入研究RHFS模型及其在强化学习领域的应用。

zip
PaLM-rlhf-pytorch-main.zip 预估大小:17个文件
folder
PaLM-rlhf-pytorch-main 文件夹
file
setup.py 969B
folder
.github 文件夹
folder
workflows 文件夹
file
python-publish.yml 1KB
folder
data 文件夹
file
enwik8.gz 34.86MB
file
README.md 99B
file
LICENSE 1KB
file
chatgpt.png 83KB
file
.gitignore 2KB
file
train.py 3KB
file
README.md 9KB
folder
palm_rlhf_pytorch 文件夹
file
utils.py 2KB
file
__init__.py 148B
file
lora.py 670B
file
palm.py 15KB
file
reward.py 3KB
file
ppo.py 20KB
file
attention.py 4KB
file
optimizer.py 1KB
zip 文件大小:34.96MB