Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/radames/ai-town-huggingface
AI town https://github.com/a16z-infra/ai-town Patches to run on Hugging Face Spaces
https://github.com/radames/ai-town-huggingface
Last synced: 11 days ago
JSON representation
AI town https://github.com/a16z-infra/ai-town Patches to run on Hugging Face Spaces
- Host: GitHub
- URL: https://github.com/radames/ai-town-huggingface
- Owner: radames
- Created: 2024-05-13T21:13:48.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2024-05-14T20:09:09.000Z (6 months ago)
- Last Synced: 2024-05-15T16:25:21.606Z (6 months ago)
- Language: TypeScript
- Homepage: https://huggingface.co/spaces/radames/ai-town
- Size: 28.3 KB
- Stars: 7
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# AI Town 🏠💻💌 on Hugging Face 🤗
[**Demo on Hugging Face Spaces**](https://huggingface.co/spaces/radames/ai-town)
AI Town is a very cool project by [Yoko](https://github.com/ykhli) et [al.](https://github.com/a16z-infra/ai-town), a virtual town with live AI characters where they can chat and socialize. You can also interact with them by sending them messages.
This repository contains a few code patches to make AI Town run on [Hugging Face 🤗 Spaces](https://huggingface.co/spaces), as well as a Dockerfile capable of running [Convex open-source backend](https://github.com/get-convex/convex-backend), the backend and frontend on a single container.
## How to run locally
Grab your Hugging Face API token from https://huggingface.co/settings/tokens
```bash
export HF_TOKEN=hf_**********
docker build -t ai-town -f Dockerfile .
docker run -ti -p 5173:5173 -e LLM_API_KEY=$HF_TOKEN ai-town
```
## How to run on Hugging Face
You can duplicate this Space https://huggingface.co/spaces/radames/ai-town?duplicate=true, add your `HF_TOKEN`
Then you can customize [patches/constants.ts](patches/constants.ts) and [patches/characters.ts](patches/characters.ts) as you wish, as well as the LLM model and embeddings model in [patches/llm.ts](patches/llm.ts).