Update README.md

README.md

@@ -46,7 +46,7 @@ Key features include:
 - **Number of Parameters**: 32.8B
 - **Number of Parameters (Non-Embedding)**: 31.2B
 - **Context Length**: 32,768 tokens natively, extensible to 131,072 with YaRN
-- **Training Data**: 107,033 synthetic medical reasoning examples + MedReason dataset (32,682 examples)
+- **Training Data**: 107,033 synthetic medical reasoning examples + [MedReason dataset](https://huggingface.co/datasets/UCSC-VLAA/MedReason) (32,682 examples)
 - **Fine-tuning Method**: DoRA + rsLoRA (Parameter-Efficient Fine-Tuning)
 - **Alignment**: Group Relative Policy Optimization (GRPO)
 
@@ -152,7 +152,7 @@ Step 6: Plan immediate management - dual antiplatelet, anticoagulation, cath lab
 ## Training Methodology
 
 ### Stage 1: Supervised Fine-Tuning (SFT)
-- **Dataset**: 107,033 synthetic medical reasoning examples + MedReason dataset
+- **Dataset**: 107,033 synthetic medical reasoning examples + [MedReason dataset](https://huggingface.co/datasets/UCSC-VLAA/MedReason)
 - **Techniques**: DoRA + rsLoRA with rank 256
 - **Focus**: Structured clinical reasoning across diagnostic, therapeutic, and prognostic scenarios
 
@@ -246,7 +246,6 @@ This model is released under the Apache 2.0 License. Please review the license t
 
 For questions about Gazal-R1, please contact:
 - **Research Team**: TachyHealth
-- **Primary Contact**: Ahmed M. Adly (amostafa@tachyhealth.com)
 - **Website**: [https://tachyhealth.com/](https://tachyhealth.com/)
 
 ---