Medical_Doctor_AI_LoRA Open-Source Medical Diagnosis Model - Free Support for Symptom Analysis and Disease Diagnosis

Medical Doctor AI LoRA Mistral 7B Instruct FullModel

Developed by ritvik77

A medical diagnosis AI model optimized through LoRA fine-tuning and 4-bit quantization technology based on the Mistral-7B language model, focusing on symptom analysis and disease diagnosis assistance.

Large Language Model

Transformers

EnglishOpen Source License:Apache-2.0 #Medical Reasoning Assistance #Low VRAM Efficient Inference #Accurate Symptom Diagnosis

Downloads 1,275

Release Time : 3/10/2025

Model Overview

This model aims to provide medical professionals with clear, evidence-supported insights to assist in clinical decision-making, particularly excelling in diagnostic analysis of symptoms such as chest pain, dizziness, and difficulty breathing.

Model Features

Accurate Symptom Diagnosis

Provides high-precision diagnostic analysis for common symptoms such as chest pain, dizziness, and difficulty breathing

Chain-of-Thought Reasoning

Utilizes CoT (Chain-of-Thought) prompting technology to achieve step-by-step medical reasoning

Efficient Resource Utilization

Significantly reduces VRAM usage through LoRA fine-tuning and 4-bit quantization, suitable for resource-limited environments

Model Capabilities

Symptom Analysis

Disease Diagnosis Assistance

Medical Reasoning

Clinical Decision Support

Use Cases

Clinical Assistance

Chest Pain Diagnosis

Analyzes possible causes of a patient's chest pain symptoms

Provides potential diagnostic directions and relevant medical evidence

Comprehensive Symptom Assessment

Conducts integrated analysis of multiple concurrent symptoms

Generates systematic diagnostic suggestions and differential diagnoses

Medical Education

Clinical Reasoning Demonstration

Demonstrates the diagnostic thought process for typical cases

Helps medical students understand clinical decision-making logic

🚀 Medical Diagnosis AI Model - Powered by Mistral-7B & LoRA

This medical diagnosis AI model, powered by Mistral-7B and LoRA, offers accurate medical diagnoses and step-by-step reasoning. It's designed to assist healthcare professionals in making better clinical decisions.

🚀 Quick Start

Use the following code to start using the model:

!pip install -q -U bitsandbytes
!pip install -q -U peft
!pip install -q -U trl
!pip install -q -U tensorboardX
!pip install -q wandb

from transformers import AutoModelForCausalLM, AutoTokenizer

# ✅ Load the uploaded model
model = AutoModelForCausalLM.from_pretrained("ritvik77/Medical_Doctor_AI_LoRA-Mistral-7B-Instruct_FullModel")
tokenizer = AutoTokenizer.from_pretrained("ritvik77/Medical_Doctor_AI_LoRA-Mistral-7B-Instruct_FullModel")

# ✅ Sample inference
prompt = "Patient reports chest pain and dizziness with nose bleeding, What’s the likely diagnosis is it cancer ?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=300)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Advanced Usage

# Advanced scenario: Using a different prompt
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("ritvik77/Medical_Doctor_AI_LoRA-Mistral-7B-Instruct_FullModel")
tokenizer = AutoTokenizer.from_pretrained("ritvik77/Medical_Doctor_AI_LoRA-Mistral-7B-Instruct")
prompt = "Patient reports a long - term cough and fatigue. What could be the diagnosis?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=300)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

✨ Features

Accurate Diagnoses: Provides accurate diagnoses for symptoms like chest pain, dizziness, and breathlessness.
Step - by - Step Reasoning: Uses Chain - of - Thought (CoT) prompting for step - by - step medical reasoning.
Efficient Inference: Reduces VRAM usage, ideal for GPUs with limited memory.

📦 Installation

!pip install -q -U bitsandbytes
!pip install -q -U peft
!pip install -q -U trl
!pip install -q -U tensorboardX
!pip install -q wandb

📚 Documentation

Model Details

Base Model: Mistral - 7B (7.7 billion parameters)
Fine - Tuning Method: LoRA (Low - Rank Adaptation)
Quantization: bnb_4bit (reduces memory footprint while retaining performance)
Original Mistral - 7B Parameters: 7.7 billion
LoRA Fine - Tuned Parameters: ~4.48% of total model parameters (~340 million)
Final Merged Model Size (bnb_4bit Quantized): ~4.5GB

Model Description

This model leverages the powerful Mistral - 7B language model, known for its strong reasoning capabilities and deep language understanding. Through LoRA fine - tuning, it excels in medical - specific tasks such as diagnosing conditions from symptoms and providing detailed medical reasoning.

Developed by: [Ritvik Gaur]
Model type: [Medical LLM]
License: Apache - 2.0
Finetuned from model: [Mistral - 7B - Instruct - v3]

Training Procedure

Training Hyperparameters

Parameter	Value	Description
Base Model	mistralai/Mistral - 7B - Instruct	Chosen for its strong reasoning capabilities.
Fine - Tuning Framework	LoRA (Low - Rank Adaptation)	Efficiently fine - tuned only ~4.48% of total parameters.
Quantization	bnb_4bit	Enabled for reduced VRAM consumption.
Train Batch Size	12	Optimized to balance GPU utilization and convergence.
Eval Batch Size	12	Matches training batch size to ensure stable evaluation.
Gradient Accumulation Steps	3	Effective batch size = 36 for improved stability.
Learning Rate	3e - 5	Lowered to ensure smoother convergence
Warmup Ratio	0.2	Gradual learning rate ramp - up for improved stability
Scheduler Type	Cosine	Ensures smooth and controlled learning rate decay
Number of Epochs	5	Balanced to ensure convergence without overfitting
Max Gradient Norm	0.5	Prevents exploding gradients
Weight Decay	0.08	Regularization for improved generalization
bf16 Precision	True	Maximizes GPU utilization and precision
Gradient Checkpointing	Enabled	Reduces memory usage during training

LoRA Configuration

Parameter	Value	Description
Rank Dimension	128	Balanced for strong expressiveness without excessive memory overhead
LoRA Alpha	128	Ensures stable gradient updates
LoRA Dropout	0.1	Helps prevent overfitting

🔧 Technical Details

The model uses the Mistral - 7B base model and fine - tunes it using LoRA. The bnb_4bit quantization is applied to reduce the memory footprint. The training hyperparameters are carefully selected to balance performance, convergence, and generalization.

📄 License

This model is licensed under the Apache - 2.0 license.

⚠️ Important Note

Please don't fully rely on this model for real - life illness diagnosis. This model is just for support of real verified health applications that require LLM.

💡 Usage Tip

Users (both direct and downstream) should be aware of the risks, biases, and limitations of the model.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご