+0
日增长
-3
周增长
-3
月增长
6,343
stars
480
forks
57
watchers
66
prs
95
issues
0
releases
README
openplayground
An LLM playground you can run on your laptop.
https://user-images.githubusercontent.com/111631/227399583-39b23f48-9823-4571-a906-985dbe282b20.mp4
Features
- Use any model from OpenAI, Anthropic, Cohere, Forefront, HuggingFace, Aleph Alpha, Replicate, Banana and llama.cpp.
- Full playground UI, including history, parameter tuning, keyboard shortcuts, and logprops.
- Compare models side-by-side with the same prompt, individually tune model parameters, and retry with different parameters.
- Automatically detects local models in your HuggingFace cache, and lets you install new ones.
- Works OK on your phone.
- Probably won't kill everyone.
Try on nat.dev
Try the hosted version: nat.dev.
How to install and run
sh
pip install openplayground
openplayground run
Alternatively, run it as a docker container:
sh
docker run --name openplayground -p 5432:5432 -d --volume openplayground:/web/config natorg/openplayground
This runs a Flask process, so you can add the typical flags such as setting a different port openplayground run -p 1235 and others.
How to run for development
sh
git clone https://github.com/nat/openplayground
cd app && npm install && npx parcel watch src/index.html --no-cache
cd server && pip3 install -r requirements.txt && cd .. && python3 -m server.app
Docker
sh
docker build . --tag "openplayground"
docker run --name openplayground -p 5432:5432 -d --volume openplayground:/web/config openplayground
First volume is optional. It's used to store API keys, models settings.
Ideas for contributions
- Add a token counter to the playground
- Add a cost counter to the playground and the compare page
- Measure and display time to first token
- Setup automatic builds with GitHub Actions
- The default parameters for each model are configured in the server/models.json file. If you find better default parameters for a model, please submit a pull request!
- Someone can help us make a homebrew package, and a dockerfile
- Easier way to install open source models directly from openplayground, with openplayground install or in the UI.
- Find and fix bugs
- ChatGPT UI, with turn-by-turn, markdown rendering, chatgpt plugin support, etc.
- We will probably need multimodal inputs and outputs at some point in 2023
llama.cpp
Adding models to openplayground
Models and providers have three types in openplayground:
- Searchable
- Local inference
- API
You can add models in server/models.json with the following schema:
Local inference
For models running locally on your device you can add them to openplayground like the following (a minimal example):
json
"llama": {
"api_key" : false,
"models" : {
"llama-70b": {
"parameters": {
"temperature": {
"value": 0.5,
"range": [
0.1,
1.0
]
},
}
}
}
}
Keep in mind you will need to add a genTop issues
#30huggingface models pending15 comments · 2023-04-08#70Add my model or API into source code?11 comments · 2023-04-25#47model error gpt4 10 comments · 2023-04-16#53What software was used to make `all-features.mp4`?7 comments · 2023-04-20#8add upload for models7 comments · 2023-04-04#36After run calling localhost:5432 there is a white page6 comments · 2023-04-10#50Help .. increase gpt4 model maximum tokens more than 8192 PLEASE5 comments · 2023-04-19#66is there an API?4 comments · 2023-04-25