1
1
Fork 0

Brought this from: https://github.com/nomic-ai/gpt4all, includes the models!

README.md

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

Discord

gpt4all-lora-demo

Run on M1 Mac (not sped up!)

Try it yourself, no additional downloads required!

git xet clone xet@xethub.com:rajatarya/gpt4all.git

cd gpt4all/chat

./gpt4all-lora-quantized-OSX-m1

# to run unfiltered model:
./gpt4all-lora-quantized-OSX-m1 -m gpt4all-lora-unfiltered-quantized.bin

Get the full repo & all models.

git xet clone xet@xethub.com:rajatarya/gpt4all.git
  • cd chat;./gpt4all-lora-quantized-OSX-m1 on M1 Mac/OSX
  • cd chat;./gpt4all-lora-quantized-linux-x86 on Linux
  • cd chat;./gpt4all-lora-quantized-win64.exe on Windows (PowerShell)
  • cd chat;./gpt4all-lora-quantized-OSX-intel on Intel Mac/OSX

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


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

  • cd chat;./gpt4all-lora-quantized-OSX-m1 -m gpt4all-lora-unfiltered-quantized.bin

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

Reproducibility

Trained LoRa Weights:

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 https://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"

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 Ceasar into a ceasar salad in iambic pentameter.

The fall of Julius Ceasar into a ceasar 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 Ceasar into a ceasar 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

GPU Interface

There are two ways to get up and running with this model on GPU.

  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 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)

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

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}},
}

Alternative Download Locations

magnet:?xt=urn:btih:1F11A9691EE06C18F0040E359361DCA0479BCB5A&dn=gpt4all-lora-quantized.bin&tr=udp%3A%2F%2Ftracker.opentrackr.org%3A1337%2Fannounce&tr=udp%3A%2F%2Fopentracker.i2p.rocks%3A6969%2Fannounce

https://the-eye.eu/public/AI/models/nomic-ai/gpt4all/gpt4all-lora-unfiltered-quantized.bin.torrent

File List Total items: 17
Name Last Commit Size Last Modified
chat Added unfiltered model 11 months ago
configs Initial copy, including basic model. 11 months ago
eval_data Initial copy, including basic model. 11 months ago
figs Initial copy, including basic model. 11 months ago
.gitattributes Initial commit 79 B 11 months ago
README.md Updated README for XetHub 7.6 KiB 11 months ago
TRAINING_LOG.md Initial copy, including basic model. 9.8 KiB 11 months ago
clean.py Initial copy, including basic model. 2.1 KiB 11 months ago
data.py Initial copy, including basic model. 4.0 KiB 11 months ago
env.yaml Initial copy, including basic model. 285 B 11 months ago
eval_figures.py Initial copy, including basic model. 791 B 11 months ago
eval_self_instruct.py Initial copy, including basic model. 5.1 KiB 11 months ago
generate.py Initial copy, including basic model. 1.9 KiB 11 months ago
gpt4all-lora-demo.gif Initial copy, including basic model. 2.6 MiB 11 months ago
read.py Initial copy, including basic model. 221 B 11 months ago
requirements.txt Initial copy, including basic model. 121 B 11 months ago
train.py Initial copy, including basic model. 7.4 KiB 11 months ago

About

Brought this from: https://github.com/nomic-ai/gpt4all, includes the models!

Repository Size

Loading repo size...

Commits 4 commits

File Types