Add model card

README.md

@@ -0,0 +1,25 @@
+---
+library_name: transformers
+tags: [zen, reasoning, chain-of-thought, hanzo]
+license: apache-2.0
+---
+# Zen4 Thinking — Deep Reasoning
+
+Dedicated reasoning model with explicit chain-of-thought capabilities.
+
+- **Developer**: [Hanzo AI](https://hanzo.ai) × [Zen LM](https://zenlm.org)
+- **Parameters**: 80B (3B active)
+- **Architecture**: MoE + CoT
+- **Context**: 131K tokens
+- **API**: [api.hanzo.ai](https://cloud.hanzo.ai)
+- **Docs**: [zenlm.org/docs/models/zen4-thinking](https://zenlm.org/docs/models/zen4-thinking)
+
+## Usage
+```python
+from hanzo import Hanzo
+client = Hanzo()
+response = client.chat.completions.create(model="zen4-thinking", messages=[{"role": "user", "content": "Solve this step by step: ..."}])
+```
+
+## Related
+- [zen-max](https://huggingface.co/zenlm/zen-max) — Base reasoning weights