README / README.md
masoudc's picture
Add prompt-router demo link (private, hosted on masoudc/)
389b51d verified
|
Raw
History Blame Contribute Delete
703 Bytes
---
title: README
emoji: πŸ†
colorFrom: purple
colorTo: indigo
sdk: static
pinned: false
---
Finetuning Qwen models to do interesting and useful things.
## Demos
**[prompt-router](https://huggingface.co/spaces/masoudc/prompt-router)** β€” a retrieval-augmented router built on [`Qwen/Qwen3-Embedding-8B`](https://huggingface.co/Qwen/Qwen3-Embedding-8B). Given a prompt, it embeds it, retrieves the most similar past prompts, and routes to the **cheapest model that will still answer well** (Qwen3-vLLM β†’ Haiku β†’ Sonnet β†’ Opus). Minimal terminal-style interface, running live on ZeroGPU.
πŸ”’ **Private Space** β€” hosted under `masoudc/` (for free ZeroGPU via PRO); request access to try it.