Giter VIP home page Giter VIP logo

llm_lora's Introduction

LLM LoRA fine-tuning

Finetune Setup

conda create --name llama2 python=3.9
conda activate llama2

# pytorch
conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.7 -c pytorch -c nvidia

# transformers
pip install git+https://github.com/huggingface/transformers@b074461ef0f54ce37c5239d30ee960ece28d11ec

# flash attention
MAX_JOBS=4 pip install flash-attn --no-build-isolation

# Remaining
pip install -r requirements.txt

# Note: If you encounter problem that is about loading datasets, try upgrade datasets package first.
pip install -U datasets

Fine-tuning

  • Single GPU training
./train_llm.sh      # Use wikitext2
./train_llm_c4.sh   # Use c4
  • Multi-GPU trainig (DDP)
./train_llm_multigpu.sh
./train_llm_c4_multigpu.sh

Batch size config

You may need to adjust batch size due to memory constraint.

Modify the arguments in train_llm.sh or train_llm_c4.sh.

    --per_device_train_batch_size 4 \
    --per_device_eval_batch_size 16 \

llm_lora's People

Contributors

yuko29 avatar

Watchers

 avatar Kostas Georgiou avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.