gpt-llama.cpp v0.2.2
gpt-llama.cpp
Demo
Real-time speedy interaction mode demo of using gpt-llama.cpp
's API + chatbot-ui (GPT-powered app) running on a M1 Mac with local Vicuna-7B
model. See all demos here.
š„ Hot Topics (4/23/2023)
- š„š„ WE MADE A DISCORD SERVER, JOIN HERE: https://discord.gg/yseR47MqpN š„š„ Update: gpt-llama.cpp bot running vicuna 7b live on the server for use!
Auto-GPT supportBasic support complete. Continued optimization work ongoing (new updates on 4/22, 4/23), track progress on this github issue- BabyAGI/TeenageAGI support
Description
gpt-llama.cpp
is an API wrapper around llama.cpp
. It runs a local API server that simulates OpenAI's API GPT endpoints but uses local llama-based models to process requests.
It is designed to be a drop-in replacement for GPT-based applications, meaning that any apps created for use with GPT-3.5 or GPT-4 can work with llama.cpp
instead.
The purpose is to enable GPT-powered apps without relying on OpenAI's GPT endpoint and use local models, which decreases cost (free) and ensures privacy (local only).
Tested platforms
- macOS (ARM)
- macOS (Intel)
- Windows
- Linux (Port :443 blocked by default, may have to change the port to 8000 to get working)
Features
gpt-llama.cpp
provides the following features:
- Drop-in replacement for GPT-based applications
- Interactive mode supported, which means that requests within the same chat context will have blazing-fast responses
- Automatic adoption of new improvements from
llama.cpp
- Usage of local models for GPT-powered apps
- Support for multiple platforms
Supported applications
The following applications (list growing) have been tested and confirmed to work with gpt-llama.cpp
:
- chatbot-ui - setup guide
- ChatGPT-Siri - setup guide
- āļø WORKS WITH FORK: Auto-GPT - setup guide here
- Issue tracking this here
- āļø WORKS WITH FORK: ai-code-translator
- See issue tracking this here
- babyagi
More applications are currently being tested, and welcome requests for verification or fixes by opening a new issue in the repo.
See all demos here.
Quickstart Installation
Prerequisite
š“š“ ā ļø DO NOT SKIP THIS STEP ā ļø š“š“
Setup llama.cpp
by following the instructions below. This is based on the llama.cpp README. You may skip if you have llama.cpp
set up already.
Mac
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
make
# install Python dependencies
python3 -m pip install -r requirements.txt
Windows
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
- Then, download the latest release of llama.cpp here
I do not know if there is a simple way to tell if you should download
avx
,avx2
oravx512
, but oldest chip foravx
and newest chip foravx512
, so pick the one that you think will work with your machine. (lets try to automate this step into the future) - Extract the contents of the zip file and copy everything in the folder (which should include
main.exe
) into your llama.cpp folder that you had just cloned. Now back to the command line
# install Python dependencies
python3 -m pip install -r requirements.txt
Test llama.cpp
Confirm that llama.cpp
works by running an example. Replace <YOUR_MODEL_BIN> with your llama model, typically named something like ggml-model-q4_0.bin
# Mac
./main -m models/7B/<YOUR_MODEL_BIN> -p "the sky is"
# Windows
main -m models/7B/<YOUR_MODEL_BIN> -p "the sky is"
It'll start spitting random BS, but you're golden if it's responding. You may now move on to 1 of the 2 below methods to get up and running.
Running gpt-llama.cpp
NPM Package
# run without installing
npx gpt-llama.cpp start
# alternatively, you can install it globally
npm i gpt-llama.cpp -g
gpt-llama.cpp start
That's it!
Run Locally
Clone the repository:
git clone https://github.com/keldenl/gpt-llama.cpp.git cd gpt-llama.cpp
- Recommended folder structure
documents āāā llama.cpp ā āāā models ā ā āāā <YOUR_.BIN_MODEL_FILES_HERE> ā āāā main āāā gpt-llama.cpp
- Recommended folder structure
Install the required dependencies:
npm install
Start the server!
# Basic usage npm start # To run on a different port # Mac PORT=8000 npm start # Windows cmd set PORT=8000 npm start # Use llama.cpp flags (use it without the "--", so instead of "--mlock" do "mlock") npm start mlock threads 8 ctx_size 1000 repeat_penalty 1 lora ../path/lora
Usage
To set up the GPT-powered app, there are 2 ways:
- To use with a documented GPT-powered application, follow supported applications directions.
- To use with a undocumented GPT-powered application, please do the following:
- Update the
openai_api_key
slot in the gpt-powered app to the absolute path of your local llama-based model (i.e. for mac,"/Users/<YOUR_USERNAME>/Documents/llama.cpp/models/vicuna/7B/ggml-vicuna-7b-4bit-rev1.bin"
). - Change the
BASE_URL
for the OpenAi endpoint the app is calling tolocalhost:443
orlocalhost:443/v1
. This is sometimes provided in the.env
file, or would require manual updating within the app OpenAi calls depending on the specific application.
- Update the
Open another terminal window and test the installation by running the below script, make sure you have a llama .bin model file ready. Test the server by running the
test-installation
script# Mac sh ./test-installion.sh
(Optional) Access the Swagger API docs at
http://localhost:443/docs
to test requests using the provided interface. Note that the authentication token needs to be set to the path of your local llama-based model (i.e. for mac,"/Users/<YOUR_USERNAME>/Documents/llama.cpp/models/vicuna/7B/ggml-vicuna-7b-4bit-rev1.bin"
) for the requests to work properly.
Obtaining and verifying the Facebook LLaMA original model and Stanford Alpaca model data
Under no circumstances should IPFS, magnet links, or any other links to model downloads be shared anywhere in this repository, including in issues, discussions, or pull requests. They will be immediately deleted.
The LLaMA models are officially distributed by Facebook and will never be provided through this repository.
Contributing
You can contribute to gpt-llama.cpp
by creating branches and pull requests to merge. Please follow the standard process for open sourcing.
License
This project is licensed under the MIT License. See the LICENSE file for more details.