Quantization made by Richard Erkhov.

Med-LLaMA3-8B - GGUF

Model creator: https://huggingface.co./YBXL/
Original model: https://huggingface.co./YBXL/Med-LLaMA3-8B/

Name	Quant method	Size
Med-LLaMA3-8B.Q2_K.gguf	Q2_K	2.96GB
Med-LLaMA3-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
Med-LLaMA3-8B.IQ3_S.gguf	IQ3_S	3.43GB
Med-LLaMA3-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
Med-LLaMA3-8B.IQ3_M.gguf	IQ3_M	3.52GB
Med-LLaMA3-8B.Q3_K.gguf	Q3_K	3.74GB
Med-LLaMA3-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
Med-LLaMA3-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
Med-LLaMA3-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
Med-LLaMA3-8B.Q4_0.gguf	Q4_0	4.34GB
Med-LLaMA3-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
Med-LLaMA3-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
Med-LLaMA3-8B.Q4_K.gguf	Q4_K	4.58GB
Med-LLaMA3-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
Med-LLaMA3-8B.Q4_1.gguf	Q4_1	4.78GB
Med-LLaMA3-8B.Q5_0.gguf	Q5_0	5.21GB
Med-LLaMA3-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
Med-LLaMA3-8B.Q5_K.gguf	Q5_K	5.34GB
Med-LLaMA3-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
Med-LLaMA3-8B.Q5_1.gguf	Q5_1	5.65GB
Med-LLaMA3-8B.Q6_K.gguf	Q6_K	6.14GB
Med-LLaMA3-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

library_name: transformers tags: []

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:

@misc{xie2024llama,
      title={Me LLaMA: Foundation Large Language Models for Medical Applications}, 
      author={Qianqian Xie and Qingyu Chen and Aokun Chen and Cheng Peng and Yan Hu and Fongci Lin and Xueqing Peng and Jimin Huang and Jeffrey Zhang and Vipina Keloth and Huan He and Lucila Ohno-Machido and Yonghui Wu and Hua Xu and Jiang Bian},
      year={2024},
      eprint={2402.12749},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}