ahmadnawaz21/Qwen2.5-1.5B-Medical-QLoRA-DPO

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 11, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

ahmadnawaz21/Qwen2.5-1.5B-Medical-QLoRA-DPO is a 1.5 billion parameter causal language model based on the Qwen2.5 architecture, specifically fine-tuned for medical decision support and clinical reasoning. Developed by Ahmad Nawaz, this model underwent a two-stage alignment process: Supervised Fine-Tuning on medical terminology and clinical flashcards, followed by Direct Preference Optimization (DPO) to enhance helpfulness and reduce non-factual outputs. It excels in generating medically relevant responses, making it suitable for specialized healthcare AI applications.

Loading preview...

Overview

ahmadnawaz21/Qwen2.5-1.5B-Medical-QLoRA-DPO is a specialized 1.5 billion parameter language model built upon the unsloth/Qwen2.5-1.5B base. Developed by Ahmad Nawaz, this model is meticulously designed for medical decision support and clinical reasoning. It leverages a two-stage fine-tuning approach to achieve its domain-specific capabilities and preference alignment.

Key Capabilities

  • Medical Domain Expertise: Imbued with extensive medical vocabulary, disease symptomatology, and diagnostic logic through Supervised Fine-Tuning (SFT) on the medalpaca/medical_meadow_medical_flashcards dataset.
  • Preference Alignment (DPO): Utilizes Direct Preference Optimization (DPO) on a subfiltered argilla/distilabel-intel-orca-dpo-pairs dataset to ensure responses are helpful, safe, and factually grounded, mitigating hallucinations.
  • Efficient Fine-Tuning: Employs 4-bit QLoRA for efficient fine-tuning, resulting in merged 16-bit floating-point weights.
  • Causal Language Modeling: Based on a Transformer architecture, capable of generating coherent and contextually relevant text.

Good for

  • Medical Decision Support Systems: Assisting healthcare professionals with diagnostic indicators and initial management steps.
  • Clinical Reasoning Applications: Developing AI tools that require understanding and processing complex medical information.
  • Specialized Medical AI Assistants: Creating chatbots or virtual assistants focused on medical queries and information retrieval.
  • Research in Medical NLP: Serving as a strong baseline or component for further research and development in medical natural language processing.

Finetunes
1 models