Apollo

Multilingual Medicine: Model, Dataset, Benchmark, Code

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

Paper •  Demo •  ApolloCorpus •  XMedBench  •  ApolloMoE

中文 | English

Update

• [2024.10.15] ApolloMoE repo released, covering 50 Languages.
• [2024.04.25] MedJamba released, train and evaluation code refer to repo.
• [2024.03.07] Paper released.
• [2024.02.12] ApolloCorpus and XMedBench is published！
• [2024.01.23] Apollo repo is published！

Results

Apollo-0.5B •  Apollo-1.8B •  Apollo-2B  •  Apollo-6B •  Apollo-7B  •  Apollo-34B •  Apollo-72B  

MedJamba

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

Usage Format

• 0.5B, 1.8B, 2B, 6B, 7B: User:{query}\nAssistant:{response}
• 34B, 72B: :{query}\n:{response}

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
          复制

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

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

          [
            [
              "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)
        复制

          [
            [
              "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

We take Gemma-2b as example

1. Download Dataset for project:

   复制

   bash 0.download_data.sh

2. Prepare test and dev for specific model:

   • Create test data for with special token, you can use ./util/check.ipynb to check models' special tokens
   复制

   bash 1.data_process_test&dev.sh

3. Prepare train data for specific model (Create tokenized data in advance):

   • You can adjust data Training order and Training Epoch in this step
   复制

   bash 2.data_process_train.sh

4. Train the model

   • If you want to train in Multi Nodes please refer to ./scripts/multi_node_train_*.sh
   复制

   bash 3.single_node_train_gemma.sh

5. (Optional) Proxy-Tuning: Directly improve model capabilities without fine-tuning

   复制

     bash src/proxy-tuning/scripts/eval/proxy_tuning.sh

6. Evaluate your model: Generate score for benchmark

   复制

   bash 4.eval.sh

7. Evaluate your model: Play with your ckpts in bash

   复制

   python ./src/evaluate/cli_demo.py --model_name='./ckpts/your/path/tfmr'

Acknowledgment

• HuatuoGPT-II
• proxy-tuning

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}
}

Star History