README.md

---
title: Qwen3.5 Reasoning Chat (Claude Distilled)
emoji: 🧠
colorFrom: blue
colorTo: indigo
sdk: gradio
app_file: app.py
pinned: false
license: apache-2.0
---

# Qwen3.5 Reasoning Chat (Claude 4.6 Distilled)

This project runs the **Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF** model using `llama-cpp-python`.

It is specifically tuned to follow a **Chain-of-Thought (CoT)** reasoning process using `<think>` tags, distilled from Claude 4.6 Opus trajectories.

## Features
- **GGUF Optimized:** Runs efficiently on CPU.
- **Reasoning First:** Designed to "think" before answering.
- **No API Key Required:** Runs the model directly within the Space environment.

## Deployment
1. Log in: `huggingface-cli login`
2. Create Space: `huggingface-cli repo create qwen3.5-reasoning --repo-type space --sdk gradio`
3. Upload: `huggingface-cli upload <username>/qwen3.5-reasoning . --repo-type space`