Durgesh Rao DURGESH716

Achieve the Impossible !!

• Bengaluru, Karnataka
• 08:47 (UTC -12:00)
• in/durgesh-rao

Pinned Loading

1. Multimodal Medical AI Fine-Tuned on Qwen-2.5-VL-7B with LoRA + Medical Distillation

   Python 1

2. Hard Reasoning Benchmark filtered with disagreement scores

   Python 1

3. MedGemma 1.5 Instruct LoRA fine-tuning + Gradio app for Real-time Interaction on CT-Scan, MRI, X-RAY images

   Python 1

4. LLaMA-8B-IT RL fine-tuning on GRPO (Grouped Relative priority Optimization) on Python Codes

   Python 1