mirror of
https://github.com/wassname/alignment-handbook.git
synced 2026-06-27 17:29:09 +08:00
d2fed11ce07ee2ab1b802c4dfa4f4ecab9de5cd9
The RLHF Handbook
Robust recipes for RLHF
Developing
To view this locally, run the following (need to point to a specific language if previewing only one section, preview/build_doc does not use the --language flag):
doc-builder preview rlhf-handbook {docs_dir} --not_python_module
Example docs_dir is ~/Documents/HuggingFace/dev/rlhf-handbook/chapters/en
Installation
Create a new conda environment with:
conda create -n rlhf-handbook python=3.10
Install the limited requirements with
pip install -r requirements.txt
Description
Languages
Python
64.1%
Jupyter Notebook
32.5%
Shell
2.7%
Makefile
0.7%