Code Monkey home page Code Monkey logo

rlhf_instructgpt's Introduction

RLHF_instructGPT

Reproduce instructGPT

Install

git clone [email protected]:LanXiu-0523/RLHF_instructGPT.git
cd RLHF_instructGPT/

python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

Download local datafile

国内huggingface连接有问题,需要将dataset和model下载到本地

cd RLHF_instructGPT/
sudo apt-get install git-lfs
mkdir datafile
cd datafile/
git lfs install

mkdir Dahoas
cd Dahoas/
git clone https://huggingface.co/datasets/Dahoas/rm-static

mkdir ../facebook
cd ../facebook/
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/facebook/opt-350m
cd opt-350m/
git lfs pull --include="*.bin"

cd ../
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/facebook/opt-1.3b
cd opt-1.3b/
git lfs pull --include="*.bin"

More:

cd RLHF_instructGPT/datafile/Dahoas
git clone https://huggingface.co/datasets/Dahoas/full-hh-rlhf
git clone https://huggingface.co/datasets/Dahoas/synthetic-instruct-gptj-pairwise

cd ../
mkdir yitingxie
cd yitingxie/
git clone https://huggingface.co/datasets/yitingxie/rlhf-reward-datasets
cd RLHF_instructGPT/datafile/
mkdir meta-llama
cd meta-llama/
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/meta-llama/Llama-2-7b-hf
cd Llama-2-7b-hf/
git lfs pull --include="*.bin"

Run

1.单机单卡:

bash train.sh sgl_gpu

2.单机多卡:

bash train.sh sgl_mach

3.多机多卡

# 首次运行
bash applications/scripts/mul_mach/apt-install.sh
bash train.sh mul_mach

Acknowledgement

This project is built upon the codebase of DeepSpeedExamples. Sincere thanks to Microsoft for their hard work!

rlhf_instructgpt's People

Contributors

lanxiu0523 avatar

Stargazers

 avatar  avatar  avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.