Page cover image

Recurv Clinical Deepseek R1

The Recurv-Clinical-Deepseek-R1 model is an upgraded version of Deepseek’s R1, specifically designed to provide accurate and contextually relevant support for healthcare professionals and researchers. This model excels at answering clinical questions, assisting in gathering patient histories, and generating detailed explanations tailored to various clinical situations through advanced instruction tuning techniques.

(Knowledge cut-off date: 22th January, 2025)

🎯 Key Features

  • Optimized for medical-specific queries across various specialties.

  • Fine-tuned for clinical and research-oriented workflows.

  • Lightweight parameter-efficient fine-tuning with safetensors format.

  • Multi-turn conversation support for context-rich interactions.

  • Generates comprehensive answers and evidence-based suggestions.


🚀 Model Card

Parameter

Details

Base Model

DeepSeek R1 Distill Llama 8B

Fine-Tuning Framework

safetensors

Dataset Size

12,632 high-quality Q&A pairs

Context Length

4,096 tokens

Training Steps

100,000

Model Size

8 billion parameters


📊 Model Architecture

Dataset Sources

The dataset comprises high-quality Q&A pairs curated from medical textbooks, research papers, and clinical guidelines.

Source
Description

PubMed

Extracted insights from open-access medical research.

Clinical Guidelines

Data sourced from WHO, CDC, and specialty-specific guidelines.

EHR-Simulated Data

Synthetic datasets modeled on real-world patient records for anamnesis workflows.

🔗 Check out the model

Recurv Medical Deepseek R1 deployed on HuggingFace; click the link below to check more detail.

Last updated