Vaibhavkr007/Llama3.2-1B-FinedTuned-MedicalQA

Model Card for Llama3.2-1B-FineTuned-MedicalQA

Model Details

Model Description

This is a fine-tuned version of the Llama-3.2-1B base model, optimized for medical question answering tasks. The model was fine-tuned using the FreedomIntelligence/medical-o1-reasoning-SFT dataset, which is specifically designed for reasoning in medical domains.

• Developed by: Meta-Llama
• Model type: Language Model
• Fine-tuned from model: meta-llama/Llama-3.2-1B
• Fine-tuned dataset: FreedomIntelligence/medical-o1-reasoning-SFT
• Languages Supported: English
• License: [Model License Information]

Model Sources

• Repository: (https://huggingface.co/meta-llama/Llama-3.2-1B)
• Dataset used for fine-tuning: FreedomIntelligence/medical-o1-reasoning-SFT

Uses

Direct Use

This model is designed to answer questions related to medical reasoning, making it useful for applications in healthcare AI systems, medical research assistants, or clinical decision support systems.

Out-of-Scope Use

This model should not be used for non-medical domains or tasks. It is also not intended for any malicious use, such as generating harmful or incorrect medical information.

Bias, Risks, and Limitations

Like all large language models, this model may carry biases inherent in the data it was trained on. It's important to evaluate its outputs carefully, especially in critical domains like healthcare, where errors can have significant consequences.

Recommendations

• Use this model for assisting with medical QA and decision support, but always verify its answers with human expertise.
• Be mindful of potential biases in healthcare-related datasets and continuously monitor the model's performance.

How to Get Started with the Model

You can use the model for medical question answering by loading it as follows:

from transformers import AutoModelForQuestionAnswering, AutoTokenizer

model_name = "Vaibhavkr007/Llama3.2-1B-FinedTuned-MedicalQA"
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)