fivetech commited on
Commit
9055c9c
·
verified ·
1 Parent(s): b4b9928

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -6
README.md CHANGED
@@ -1,11 +1,22 @@
1
  ---
2
- title: Multi Agent Debate MiMo WebGPU
3
- emoji: 🌍
4
- colorFrom: green
5
- colorTo: pink
6
  sdk: static
 
7
  pinned: false
8
- short_description: Agentes debatiendo con MiMo en tu navegador
 
 
9
  ---
10
 
11
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
1
  ---
2
+ title: Multi-Agent Debate - MiMo WebGPU
3
+ emoji: 🤖
4
+ colorFrom: blue
5
+ colorTo: purple
6
  sdk: static
7
+ app_file: index.html
8
  pinned: false
9
+ models:
10
+ - bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF
11
+ - XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
12
  ---
13
 
14
+ # Multi-Agent Debate — MiMo-V2.6-Distill-Qwen-9B (WebGPU)
15
+
16
+ Several configurable agents share one in-browser model and debate a topic you propose,
17
+ round by round. Built with [wllama](https://github.com/ngxson/wllama) (MIT); inspired by the
18
+ [localellm.com](https://localellm.com) WebGPU widget. Model:
19
+ [MiMo-V2.6-Distill-Qwen-9B](https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B) (MIT, Xiaomi).
20
+
21
+ Inference runs in your browser (WebGPU when available, otherwise CPU/WASM). The browser only
22
+ contacts Hugging Face to download the model (~5.8 GB the first time) and jsDelivr for libraries.