magpie

Overview

Installation

Build environment

git clone https://github.com/magpie-align/magpie.git
cd magpie
conda create -n magpie python=3.10 -y
conda activate magpie
pip install -r requirements.txt

Get access to Llama-3 models from 🤗 Huggingface

You can apply for Llama-3 model access here. To login in the terminal, enter:

huggingface-cli login

then enter your Huggingface private key beginning with “hf_”.

Toy Example

Play with Jupyter Notebook

The toy example can be found in demo.ipynb. Have fun!

Batched SFT Data Generation

We use Llama-3-8B-Instruct as an example to demonstrate the batched SFT data generation process. To run batched generation, you can simply run:

cd scripts
bash magpie.sh

The script will generate both instructions and responses in the data folder. It has been tested on an RTX 4090 24G GPU. If you are using GPUs with less memory, consider implementing quantization.

We also provide scripts for other models in the scripts folder. You can use this navigation to find specific Magpie scripts. Note that for model sizes greater than 8B, you may need 4*A100 GPUs to run the scripts.

Batched Multi-turn Data Generation [Optional]

After generating instruction-response pairs, you can extend them to multi-turn conversations. To do so, simply run the following command:

bash magpie-multi-turn.sh ***_ins_res.json

where ***_ins_res.json is the single-turn instruction-response pairs generated in the previous step.

Dataset Filtering

1. Tagging

To tag the generated instruction-response pairs, you can run:

cd scripts
bash unitag.sh ***_ins_res.json all

This script will automatically generate quality, difficulty, task category, safety, reward, and language for the generated dataset. You can also generate one tag at a time. For example, if you just want to generate the safety label using device 0, you can run:

cd scripts
bash unitag.sh ***_ins_res.json safety 0

2. Data Concatenation and Converting

You may generate datasets with different generation configurations. We provide a Jupyter notebook here for concatenating all datasets and converting them to ShareGPT format, which is fully supported by Axolotl for fine-tuning.

3. Removing Repetition

Once you have a full dataset converted to ShareGPT format, you can calculate the minimum neighbor distance of each instruction and remove repetitions. To do so, run:

cd exp
python gen_dis.py --input_file ***_sharegpt.jsonl

where ***_sharegpt.jsonl is the dataset path obtained in the previous step. The Python script will take care of building the FAISS index and calculating the minimum distance.

4. Design and Apply Your Filter

We provide a Jupyter notebook here for simple filtering. You can adjust the filtering parameters to design and apply your own filter based on your needs.

Preference Data Generation

To generate preference data, first prepare filtered instructions following the steps outlined above. For the expected format, please refer to our example here.

Next, please use our provided scripts here to generate multiple responses and compute their corresponding rewards. Finally, your can process the data and upload it to Huggingface using this Jupyter notebook.

Fine-tuning

Please take a look at the recipes directory for instructions and our Magpie model recipes.

Citation

If you find the model, data, or code useful, please cite our paper 🤩:

@article{xu2024magpie,
  title={Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing},
  author={Zhangchen Xu and Fengqing Jiang and Luyao Niu and Yuntian Deng and Radha Poovendran and Yejin Choi and Bill Yuchen Lin},
  journal={ArXiv},
  year={2024},
  volume={abs/2406.08464},
  url={https://api.semanticscholar.org/CorpusID:270391432}
}

Star History