Update README.md

README.md

@@ -1,3 +1,90 @@
----
-license: mit
----
+---
+license: mit
+base_model:
+- Qwen/Qwen3-1.7B
+tags:
+- gguf
+- quantized
+- medical
+---
+
+# 🧠 Qwen3-1.7B-MedicalDataset-GGUF
+
+A quantized GGUF-format version of [Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B), fine-tuned on a medical dataset to assist with healthcare-related tasks. Packaged in GGUF format for use with efficient inference engines like `llama.cpp`. Released by **XformAI-India**.
+
+---
+
+## 📌 Model Details
+
+- **Base Model**: Qwen3-1.7B
+- **Format**: GGUF (quantized)
+- **Quantization Types**: Multiple 
+- **Precision**: 2-8 bit quantized
+- **Use Case**: Low-resource and edge device inference for medical AI applications
+
+---
+
+## 🧪 Intended Use
+
+This quantized model is intended for:
+
+- Medical Q&A on low-resource devices
+- Offline chatbot usage in healthcare education
+- Mobile inference for healthcare reasoning
+
+---
+
+## 🚫 Limitations & Disclaimer
+
+> ⚠️ **This model is not intended for clinical use.**
+
+- Not suitable for real-time diagnostics or emergency decisions.
+- May produce inaccurate or hallucinated medical information.
+- Use for research and prototyping only.
+
+---
+
+## 🛠 How to Use
+
+Run with `llama.cpp`:
+
+```bash
+./main -m qwen3-1.7b-medical-q4_k_m.gguf -p "Explain symptoms of hypertension."
+```
+
+Or from Python using `llama-cpp-python`:
+
+```python
+from llama_cpp import Llama
+
+llm = Llama(model_path="qwen3-1.7b-medical-q4_k_m.gguf")
+output = llm("What are treatment options for Type 2 Diabetes?", max_tokens=200)
+print(output)
+```
+
+---
+
+## 🏗 Training Info (Base Fine-Tuning)
+
+- **Dataset**: FreedomIntelligence/medical-o1-reasoning-SFT
+- **Epochs**: 3
+- **Batch Size**: 8
+- **Learning Rate**: 2e-5
+- **Framework**: PyTorch + Transformers
+
+---
+
+## 🧠 Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{qwen3medicalgguf2025,
+  title={Qwen3-1.7B-MedicalDataset-GGUF: A Quantized Medical AI Model},
+  author={XformAI-India},
+  year={2025},
+  url={https://huggingface.co/XformAI-india/Qwen3-1.7B-medicaldataset-gguf}
+}
+```
+
+---