MediNote-7B: Specialized Clinical Note Generation

MediNote-7B is a 7 billion parameter causal decoder-only transformer language model, developed by Antoine Bonnet and Paul Boulenger. It is part of the MediNote suite of open-source medical Large Language Models (LLMs) and is specifically fine-tuned from the Meditron-7B.v1.0 foundation model.

Key Capabilities

• Clinical Note Generation: The primary function of MediNote-7B is to generate clinical notes based on patient-doctor conversation transcripts.
• Specialized Medical LLM: It is designed for medical text processing, leveraging its fine-tuning on a medical foundation model.
• English Language Support: The model operates exclusively in English.
• Context Length: Processes inputs up to 2,000 tokens.

Use Cases and Limitations

MediNote-7B is suitable for experimentation and understanding its capabilities in generating clinical notes. However, it is explicitly stated that the model is not yet robust enough for direct use in a real clinical setting or production environments where it might impact people. It is intended for research and development purposes rather than live clinical applications.