Skip to content

wilfrid51/llm-container

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
deploy-demos
deploy-demos
 
 
instructOR-xz
instructOR-xz
 
 
rlhf-ppo
rlhf-ppo
 
 
run_config
run_config
 
 
sft-data-construction
sft-data-construction
 
 
triton-deploy
triton-deploy
 
 
.gitignore
.gitignore
 
 
README.md
README.md
 
 
data_collators.py
data_collators.py
 
 
data_filter.py
data_filter.py
 
 
deploy_settings.sh
deploy_settings.sh
 
 
download_model.py
download_model.py
 
 
iFT-post.py
iFT-post.py
 
 
inference-model.py
inference-model.py
 
 
process.py
process.py
 
 
requirements.txt
requirements.txt
 
 
reward-post-bloom.py
reward-post-bloom.py
 
 
reward_model.py
reward_model.py
 
 
rlhf-post-bloom.py
rlhf-post-bloom.py
 
 
run-reward.sh
run-reward.sh
 
 
run-rlhf.sh
run-rlhf.sh
 
 
run.sh
run.sh
 
 
source
source
 
 
test.sh
test.sh
 
 
大模型“不完全”修炼手册——从训练、评测到应用搭建.pdf
大模型“不完全”修炼手册——从训练、评测到应用搭建.pdf
 
 

Repository files navigation

Complete docs

detailed full doc for everything/完全体文档

Install envs

first install pytorch2.0 https://pytorch.org/get-started/locally/ then install others pip install -r requirements.txt

deploy necessary settings

run train SFT model

bash run.sh

run train Reward model

bash run-reward.sh

run train RLHF model

bash run-rlhf.sh

Prepare data

SFT data

refer sft-data-construction

reward data and RLHF data

refer rlhf-ppo

About

No description, website, or topics provided.

Resources

Readme
Activity

Stars

1 star

Watchers

0 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages