Model Card for Med-LLaMA3-8B
Model Details
Model Description
Med-LLaMA3-8B is an 8-billion parameter medical language model that has undergone continual pre-training on LLaMA3-8B architecture using large-scale open-sourced medical data.
Training Details
Med-LLaMA3-8B is trained on a large-scale dataset comprising: medical books, medical literature, clinical guidelines and a small portion of general domain data It is a study extension based on our previous Me-LLaMA paper: https://arxiv.org/pdf/2402.12749
If you use the model, please cite the following papers: