Multilingual Medicine: English, Chinese, French, Hindi, Spanish, Hindi, Arabic β’ 7 items β’ Updated β’ 1
Multilingual Medicine: Model, Dataset, Benchmark, Code
Covering English, Chinese, French, Hindi, Spanish, Hindi, Arabic So far
π¨π»βπ»Github β’π Paper β’ π Demo β’ π€ ApolloCorpus β’ π€ XMedBench
δΈζ | English
π Update
- [2024.03.07] Paper released.
- [2024.02.12] ApolloCorpus and XMedBench is publishedοΌπ
- [2024.01.23] Apollo repo is publishedοΌπ
Results
π€Apollo-0.5B β’ π€ Apollo-1.8B β’ π€ Apollo-2B β’ π€ Apollo-6B β’ π€ Apollo-7B
π€ Apollo-0.5B-GGUF β’ π€ Apollo-2B-GGUF β’ π€ Apollo-6B-GGUF β’ π€ Apollo-7B-GGUF
Usage Format
User:{query}\nAssistant:{response}<|endoftext|>
Dataset & Evaluation
Dataset π€ ApolloCorpus
Evaluation π€ XMedBench
Results reproduction
Citation
Please use the following citation if you intend to use our dataset for training or evaluation:
@misc{wang2024apollo,
title={Apollo: Lightweight Multilingual Medical LLMs towards Democratizing Medical AI to 6B People},
author={Xidong Wang and Nuo Chen and Junyin Chen and Yan Hu and Yidong Wang and Xiangbo Wu and Anningzhe Gao and Xiang Wan and Haizhou Li and Benyou Wang},
year={2024},
eprint={2403.03640},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
- Downloads last month
- 79
Safetensors
Model size
3B params
Tensor type
F32
Β·
Model tree for FreedomIntelligence/Apollo-2B
Quantizations
5 models