drvivekpoojary/Open-GVP-Qwen2.5-14B-Instruct
drvivekpoojary/Open-GVP-Qwen2.5-14B-Instruct is a 14.8 billion parameter Qwen2.5-14B model fine-tuned by Dr. Vivek Poojary. It is specialized in Good Pharmacovigilance Practices (GVP) guidelines from the European Medicines Agency (EMA), trained on approximately 15,000 high-quality Q&A pairs. This model excels at interpreting GVP modules and supporting pharmacovigilance operations, particularly when integrated into a RAG pipeline with official GVP documents.
Loading preview...
Open-GVP-Qwen2.5-14B-Instruct Overview
This model is a domain-adapted version of Qwen/Qwen2.5-14B-Instruct, fine-tuned by Dr. Vivek Poojary. It specializes in Good Pharmacovigilance Practices (GVP) guidelines issued by the European Medicines Agency (EMA), covering all GVP Modules and related Addendums. The model was trained using LoRA on a curated dataset of approximately 15,000 high-quality question-answer pairs derived from official EMA GVP documents.
Key Capabilities
- GVP Knowledge Assistant: Answers questions on GVP modules, definitions, and requirements.
- PV Staff Training: Supports training and onboarding of pharmacovigilance team members.
- RAG Pipeline Integration: Designed to perform best as a generator within a Retrieval-Augmented Generation (RAG) pipeline, leveraging official GVP PDF documents.
- Internal Regulatory Chatbot: Suitable for powering company-internal PV compliance assistants.
- Offline & Low-Resource Deployment: Available in merged Safetensors and GGUF (BF16, Q8_0, Q6_K) formats, enabling local and CPU-friendly deployment.
Important Considerations
This model is intended for research, educational, and internal professional support purposes only. It is not recommended for standalone regulatory decision-making or high-stakes compliance without human review. Users should always verify outputs with qualified pharmacovigilance professionals, as the model may produce incomplete or inaccurate responses.