GPT4All

Demo, data and code to train an assistant-style large language model

📗 Technical Report

Try it yourself

You can download pre-compiled LLaMa C++ Interactive Chat binaries here:

• OSX
• Intel/Windows

and the model

• gpt4all-quantized

Place the binary and quantized model in the same directory and start chatting!

To compile for custom hardware, see our fork of the Alpaca C++ repo.

Reproducibility

Trained LoRa Weights:

• gpt4all-lora: https://huggingface.co/nomic-ai/gpt4all-lora
• gpt4all-lora-epoch-2 https://huggingface.co/nomic-ai/gpt4all-lora-epoch-2

Raw Data:

• Training Data Without P3
• Full Dataset with P3

We are not distributing a LLaMa 7B checkpoint.

You can reproduce our trained model by doing the following:

Setup

Clone the repo

git clone --recurse-submodules [email protected]:nomic-ai/gpt4all.git

git submodule configure && git submodule update

Setup the environment

python -m pip install -r requirements.txt

cd transformers
pip install -e . 

cd ../peft
pip install -e .

Training

accelerate launch --dynamo_backend=inductor --num_processes=8 --num_machines=1 --machine_rank=0 --deepspeed_multinode_launcher standard --mixed_precision=bf16  --use_deepspeed --deepspeed_config_file=configs/deepspeed/ds_config.json train.py --config configs/train/finetune-7b.yaml

Generate

python generate.py --config configs/generate/generate.yaml --prompt "Write a script to reverse a string in Python

If you utilize this reposistory, models or data in a downstream project, please consider citing it with:

@misc{gpt4all,
  author = {Yuvanesh Anand and Zach Nussbaum and Brandon Duderstadt and Benjamin Schmidt and Andriy Mulyar},
  title = {GPT4All: Training an Assistant-style Chatbot with Large Scale Data Distillation from GPT-3.5-Turbo},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/nomic-ai/gpt4all}},
}