暂无描述

Eric Wang 357ec81a17 decapoda 3 年之前
.gitignore 26f64780ad initial commit 3 年之前
DATA_LICENSE 63121244c8 Licenses and whatnot 3 年之前
LICENSE 63121244c8 Licenses and whatnot 3 年之前
README.md 357ec81a17 decapoda 3 年之前
alpaca_data.json 26f64780ad initial commit 3 年之前
conversion.py 26f64780ad initial commit 3 年之前
finetune.py 357ec81a17 decapoda 3 年之前
generate.py 357ec81a17 decapoda 3 年之前
iteration.ipynb 26f64780ad initial commit 3 年之前
lengths.ipynb 26f64780ad initial commit 3 年之前
loss.ipynb 357ec81a17 decapoda 3 年之前

README.md

alpaca-lora (WIP)

This repository contains code for reproducing the Stanford Alpaca results. Users will need to be ready to fork transformers.

Setup

  1. Install dependencies (install zphang's transformers fork)

    pip install -q datasets accelerate loralib sentencepiece
    
    pip install -q git+https://github.com/zphang/transformers@llama_push
    pip install -q git+https://github.com/huggingface/peft.git
    
  2. Install bitsandbytes from source

Inference

See generate.py.

Training

Under construction.