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

🐍 Official Python Bindings

💻 Official Typescript Bindings

🦜️🔗 Official Langchain Backend

Discord

Run on M1 Mac (not sped up!)

Try it yourself

Here's how to get started with the CPU quantized GPT4All model checkpoint:

1. Download the gpt4all-lora-quantized.bin file from Direct Link or [Torrent-Magnet].
2. Clone this repository, navigate to chat, and place the downloaded file there.
3. Run the appropriate command for your OS:
   • M1 Mac/OSX: cd chat;./gpt4all-lora-quantized-OSX-m1
   • Linux: cd chat;./gpt4all-lora-quantized-linux-x86
   • Windows (PowerShell): cd chat;./gpt4all-lora-quantized-win64.exe
   • Intel Mac/OSX: cd chat;./gpt4all-lora-quantized-OSX-intel

For custom hardware compilation, see our llama.cpp fork.

---

Find all compatible models in the GPT4All Ecosystem section.

Secret Unfiltered Checkpoint - [Torrent]

This model had all refusal to answer responses removed from training. Try it with:

• M1 Mac/OSX: cd chat;./gpt4all-lora-quantized-OSX-m1 -m gpt4all-lora-unfiltered-quantized.bin
• Linux: cd chat;./gpt4all-lora-quantized-linux-x86 -m gpt4all-lora-unfiltered-quantized.bin
• Windows (PowerShell): cd chat;./gpt4all-lora-quantized-win64.exe -m gpt4all-lora-unfiltered-quantized.bin
• Intel Mac/OSX: cd chat;./gpt4all-lora-quantized-OSX-intel -m gpt4all-lora-unfiltered-quantized.bin

---

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

Python Client

CPU Interface

To run GPT4All in python, see the new official Python bindings.

The old bindings are still available but now deprecated. They will not work in a notebook environment. To get running using the python client with the CPU interface, first install the nomic client using pip install nomic Then, you can use the following script to interact with GPT4All:

from nomic.gpt4all import GPT4All
m = GPT4All()
m.open()
m.prompt('write me a story about a lonely computer')

GPU Interface

There are two ways to get up and running with this model on GPU. The setup here is slightly more involved than the CPU model.

1. clone the nomic client repo and run pip install .[GPT4All] in the home dir.
2. run pip install nomic and install the additional deps from the wheels built here

Once this is done, you can run the model on GPU with a script like the following:

from nomic.gpt4all import GPT4AllGPU
m = GPT4AllGPU(LLAMA_PATH)
config = {'num_beams': 2,
          'min_new_tokens': 10,
          'max_length': 100,
          'repetition_penalty': 2.0}
out = m.generate('write me a story about a lonely computer', config)
print(out)

Where LLAMA_PATH is the path to a Huggingface Automodel compliant LLAMA model. Nomic is unable to distribute this file at this time. We are working on a GPT4All that does not have this limitation right now.

You can pass any of the huggingface generation config params in the config.

GPT4All Compatibility Ecosystem

Edge models in the GPT4All Ecosystem. Please PR as the community grows. Feel free to convert this to a more structured table.

• gpt4all [MD5 Signature]
  • gpt4all-ggml-converted [MD5 Signature]
• gpt4all-unfiltered [MD5 Signature]
• ggml-vicuna-7b-4bit
• vicuna-13b-GPTQ-4bit-128g
• LLaMa-Storytelling-4Bit

Roadmap

Short Term

• (IN PROGRESS) Train a GPT4All model based on GPTJ to alleviate llama distribution issues.
• (IN PROGRESS) Create improved CPU and GPU interfaces for this model.
• (NOT STARTED) Integrate llama.cpp bindings
• (NOT STARTED) Create a good conversational chat interface for the model.
• (NOT STARTED) Allow users to opt in and submit their chats for subsequent training runs

Medium Term

• (NOT STARTED) Integrate GPT4All with Atlas to allow for document retrieval.
  • BLOCKED by GPT4All based on GPTJ
• (NOT STARTED) Integrate GPT4All with Langchain.
• (IN PROGRESS) Build easy custom training scripts to allow users to fine tune models.

Long Term

• (NOT STARTED) Allow anyone to curate training data for subsequent GPT4All releases using Atlas.
• (IN PROGRESS) Democratize AI.

Reproducibility

Trained LoRa Weights:

• gpt4all-lora (four full epochs of training): https://huggingface.co/nomic-ai/gpt4all-lora
• gpt4all-lora-epoch-2 (three full epochs of training) https://huggingface.co/nomic-ai/gpt4all-lora-epoch-2

Raw Data:

• Training Data Without P3
  • Explorer: https://atlas.nomic.ai/map/gpt4all_data_clean_without_p3
• Full Dataset with P3
  • Explorer: https://atlas.nomic.ai/map/gpt4all_data_clean

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 https://github.com/nomic-ai/gpt4all.git
git submodule update --init

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"

Need Help?

Join the Discord and ask for help in #gpt4all-help

Sample Generations

Provide instructions for the given exercise. Leg Raises

Leg Raises

1. Stand with your feet shoulder-width apart and your knees slightly bent.
2. Raise your arms straight out in front of you.
3. Slowly bend your knees and raise your heels off the ground.
4. Hold this position for a count of 3, then slowly lower your heels back to the ground.
5. Repeat the exercise 10 times.
6. Do not let your knees go beyond your toes.
7. Keep your back straight and your abdominal muscles engaged.
8. Do not let your hips sag or your back arch.
9. Keep your arms straight and your elbows locked.
10. Do not let your head drop or your shoulders rise.
11. Breathe normally throughout the exercise.
12. Rest for 30 seconds before repeating the exercise.
13. Gradually increase the number of repetitions as you become stronger.

A color description has been provided. Find the CSS code associated with that color. A light red color with a medium light shade of pink

The CSS code associated with the color provided is: #FF6347

Come up with an interesting idea for a new movie plot. Your plot should be described with a title and a summary.

1. The title of your movie plot should be "The Last Stand".
2. The summary of your movie plot should be: A group of mercenaries are hired to protect a small town from a dangerous criminal who is on the run. However, the town's sheriff is not willing to let them take over and decides to take matters into his own hands.

Reverse a string in python.

In Python, you can reverse a list or tuple by using the reversed() function on it. Here's an example of how to use this method with strings:

my_string = "Hello World" # Define your original string here
reversed_str = my_string[::-1]   # Use a slice and negative index for reverse order
print(reversed_str)     # Output will be reversed version of the inputted string.

List 10 dogs.

1. Labrador Retriever
2. Golden Retriever
3. Beagle
4. Poodle
5. German Shepherd
6. Bulldog
7. Rottweiler
8. Boxer
9. Shih Tzu
10. Pug

Write me a poem about the fall of Julius Caesar into a caesar salad in iambic pentameter.

The fall of Julius Caesar into a caesar salad
In iambic pentameter,
The mighty Roman emperor
Fell into a salad of lettuce and croutons,
His empire crumbling around him,
As he was devoured by the hungry diners.
The once mighty emperor
Was now just a salad topping,
His legacy reduced to a mere garnish,
As he was consumed by the masses.
The fall of Julius Caesar into a caesar salad,
In iambic pentameter,
Was a tragic end to a great man,
Who had once ruled the world with an iron fist.
But now, he was just a salad topping,
His legacy reduced to a mere garnish,
As he was consumed by the masses.

What is a three word topic describing the following keywords: baseball, football, soccer:

Sports, athletics, games

Citation

If you utilize this repository, 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}},
}