GPT4All

Demo, data and code to train an assistant-style large language model with ~800k GPT-3.5-Turbo Generations based on LLaMa

📗 Technical Report

Run on M1 Mac (not sped up!)

Try it yourself

Clone this repository down and download the CPU quantized gpt4all model.

gpt4all-quantized

Place the quantized model in the chat directory and start chatting by running:

./chat/gpt4all-lora-quantized-OSX-m1 on M1 Mac/OSX
./chat/gpt4all-lora-quantized-linux-x86 on Windows/Linux

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

Note: the full model on GPU (16GB of RAM required) performs much better in our qualitative evaluations.

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:

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 git@github.com: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}},
}

2.8 KiB Raw Blame History