Medical-Phi2-GGUF

This is a fine-tuned version of the microsoft/phi-2 model, specialized for summarizing medical dialogues. It was trained on a combination of three publicly available medical conversation datasets.

This repository contains the quantized GGUF model file for easy use on local CPUs, as well as the original LoRA adapter for further development.

Model Details

• Base Model: microsoft/phi-2
• Training Datasets:
  • UCSD26/medical_dialog
  • FunDialogues/healthcare-minor-consultation
  • omi-health/medical-dialogue-to-soap-summary
• Fine-tuning Method: QLoRA

Intended Use

This model is designed to act as a medical assistant capable of reading a doctor-patient dialogue and generating a concise summary. It is intended for educational or research purposes to understand how language models can process clinical conversations.

It is not a medical professional and should not be used for real medical advice or diagnosis.

How to Use This GGUF Model

The primary file is phi2_medical_Q4_K_M.gguf. You can run this file on your local computer using tools like LM Studio, Ollama, or llama.cpp.

Using with LM Studio

1. Download and install LM Studio.
2. In the app's search bar, look for Prithwiraj731/Medical-Phi2-GGUF.
3. Download the phi2_medical_Q4_K_M.gguf file.
4. Go to the Chat tab (💬), select the model at the top, and start your conversation!

Using with Ollama

1. Download and install Ollama.
2. Create a file named Modelfile (no extension) and paste the following into it:

   FROM ./phi2_medical_Q4_K_M.gguf
   TEMPLATE "<start_of_turn>user\n{{ .Prompt }}<end_of_turn>\n<start_of_turn>model\n"
   

3. Place this Modelfile in the same directory as the GGUF file you downloaded.
4. Open your terminal and run the command:

   ollama create MedicalPhi2 -f ./Modelfile
   

5. You can now chat with the model by running:

   ollama run MedicalPhi2
   

---

Model fine-tuned by Prithwiraj731.