|
Download README.md from fivetech/Multi-Agent-Debate-MiMo-WebGPU: direct link, hf CLI and curl.
- Browser
- Download file 828 Bytes
-
https://huggingface.co/spaces/fivetech/Multi-Agent-Debate-MiMo-WebGPU/resolve/main/README.md
- Command line
-
hf download hf://spaces/fivetech/Multi-Agent-Debate-MiMo-WebGPU/README.md
-
curl -L -o README.md https://huggingface.co/spaces/fivetech/Multi-Agent-Debate-MiMo-WebGPU/resolve/main/README.md
828 Bytes
metadata
title: Multi-Agent Debate - MiMo WebGPU
emoji: 🤖
colorFrom: blue
colorTo: purple
sdk: static
app_file: index.html
pinned: false
models:
- bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF
- XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
Multi-Agent Debate — MiMo-V2.6-Distill-Qwen-9B (WebGPU)
Several configurable agents share one in-browser model and debate a topic you propose, round by round. Built with wllama (MIT); inspired by the localellm.com WebGPU widget. Model: MiMo-V2.6-Distill-Qwen-9B (MIT, Xiaomi).
Inference runs in your browser (WebGPU when available, otherwise CPU/WASM). The browser only contacts Hugging Face to download the model (~5.8 GB the first time) and jsDelivr for libraries.