FreedomIntelligence/Apollo-7B-GGUF

Multilingual Medicine: Model, Dataset, Benchmark, Code

Covering English, Chinese, French, Hindi, Spanish, Hindi, Arabic So far

👨🏻‍💻Github •📃 Paper • 🌐 Demo • 🤗 ApolloCorpus • 🤗 XMedBench
中文 | English

🌈 Update

• [2024.04.28] We have updated multiple versions of the Apollo-7B GGUF model.
• [2024.03.07] Paper released.
• [2024.02.12] ApolloCorpus and XMedBench is published！🎉
• [2024.01.23] Apollo repo is published！🎉

Overview

Type	Size/GB	Notes
Q2_K	3.6
IQ3_XS	3.9
IQ3_S	4.1	beats Q3_K*
Q3_K_S	4.1
IQ3_M	4.2
Q3_K_M	4.5	lower quality
Q3_K_L	4.8
IQ4_XS	4.9
Q4_K_S	5.1	fast, recommended
Q4_K_M	5.4	fast, recommended
Q5_K_S	6.1
Q5_K_M	6.2
Q6_K	7.1	very good quality
Q8_0	9.2	fast, best quality, but very large

Results

🤗Apollo-0.5B • 🤗 Apollo-1.8B • 🤗 Apollo-2B • 🤗 Apollo-6B • 🤗 Apollo-7B

🤗 Apollo-0.5B-GGUF • 🤗 Apollo-2B-GGUF • 🤗 Apollo-6B-GGUF • 🤗 Apollo-7B-GGUF

Dataset & Evaluation

• Dataset 🤗 ApolloCorpus

  Click to expand

  

  • Zip File

  • Data category

    • Pretrain:

      • data item:

        • json_name: {data_source}{language}{data_type}.json

        • data_type: medicalBook, medicalGuideline, medicalPaper, medicalWeb(from online forum), medicalWiki

        • language: en(English), zh(chinese), es(spanish), fr(french), hi(Hindi)

        • data_type: qa(generated qa from text)

        • data_type==text: list of string

          [
            "string1",
            "string2",
            ...
          ]
          

        • data_type==qa: list of qa pairs(list of string)

          [
            [
              "q1",
              "a1",
              "q2",
              "a2",
              ...
            ],
            ...
          ]
          

    • SFT:

      • json_name: {data_source}_{language}.json

      • data_type: code, general, math, medicalExam, medicalPatient

      • data item: list of qa pairs(list of string)

          [
            [
              "q1",
              "a1",
              "q2",
              "a2",
              ...
            ],
            ...
          ]
        

• Evaluation 🤗 XMedBench

  Click to expand

  • EN:

    • MedQA-USMLE
    • MedMCQA
    • PubMedQA: Because the results fluctuated too much, they were not used in the paper.
    • MMLU-Medical
      • Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine

  • ZH:

    • MedQA-MCMLE
    • CMB-single: Not used in the paper
      • Randomly sample 2,000 multiple-choice questions with single answer.
    • CMMLU-Medical
      • Anatomy, Clinical_knowledge, College_medicine, Genetics, Nutrition, Traditional_chinese_medicine, Virology
    • CExam: Not used in the paper
      • Randomly sample 2,000 multiple-choice questions

  • ES: Head_qa

  • FR: Frenchmedmcqa

  • HI: MMLU_HI

    • Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine

  • AR: MMLU_Ara

    • Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine

Results reproduction

Click to expand

Waiting for Update

Acknowledgment

We sincerely thank mradermacher for the assistance in providing multiple versions of the Apollo-7B GGUF model!

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}
}