README.md

metadata

license: apache-2.0
datasets:
  - FreedomIntelligence/ApolloMoEDataset
language:
  - ar
  - en
  - zh
  - ko
  - ja
  - mn
  - th
  - vi
  - lo
  - mg
  - de
  - pt
  - es
  - fr
  - ru
  - it
  - hr
  - gl
  - cs
  - co
  - la
  - uk
  - bs
  - bg
  - eo
  - sq
  - da
  - sa
  - 'no'
  - gn
  - sr
  - sk
  - gd
  - lb
  - hi
  - ku
  - mt
  - he
  - ln
  - bm
  - sw
  - ig
  - rw
  - ha
metrics:
  - accuracy
base_model:
  - microsoft/Phi-3-mini-4k-instruct
pipeline_tag: question-answering
tags:
  - biology
  - medical

Covering 12 Major Languages including English, Chinese, French, Hindi, Spanish, Arabic, Russian, Japanese, Korean, German, Italian, Portuguese and 38 Minor Languages So far.

📃 Paper • 🌐 Demo • 🤗 ApolloMoEDataset • 🤗 ApolloMoEBench • 🤗 Models • 🌐 Apollo • 🌐 ApolloMoE

🌈 Update

• [2024.10.15] ApolloMoE repo is published！🎉

Architecture

Click to view the MoE routing image

Results

Dense

🤗 Apollo2-0.5B • 🤗 Apollo2-1.5B • 🤗 Apollo2-2B • 🤗 Apollo2-3.8B • 🤗 Apollo2-7B • 🤗 Apollo2-9B

Click to view the Dense Models Results

Post-MoE

🤗 Apollo-MoE-0.5B • 🤗 Apollo-MoE-1.5B • 🤗 Apollo-MoE-7B

Click to view the Post-MoE Models Results

​

Usage Format

Apollo2

• 0.5B, 1.5B, 7B: User:{query}\nAssistant:{response}<|endoftext|>
• 2B, 9B: User:{query}\nAssistant:{response}<eos>
• 3.8B: <|user|>\n{query}<|end|><|assisitant|>\n{response}<|end|>

Apollo-MoE

• 0.5B, 1.5B, 7B: User:{query}\nAssistant:{response}<|endoftext|>

Dataset & Evaluation

• Dataset 🤗 ApolloMoEDataset

  Click to expand

  

  • Data category

• Evaluation 🤗 ApolloMoEBench

  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
    • [MMLU_FR]
      • Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine

  • HI: MMLU_HI

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

  • AR: MMLU_AR

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

  • JA: IgakuQA

  • KO: KorMedMCQA

  • IT:

    • MedExpQA
    • [MMLU_IT]
      • Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine

  • DE: BioInstructQA: German part

  • PT: BioInstructQA: Portuguese part

  • RU: RuMedBench

​
​

Results reproduction

Click to expand

We take Gemma-2b as example

1. Download Dataset for project:

   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

   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

   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

   bash 3.single_node_train_gemma.sh
   

5. Evaluate your model: Generate score for benchmark

   bash 4.eval.sh
   

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

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

Citation

Please use the following citation if you intend to use our dataset for training or evaluation:

@misc{zheng2024efficientlydemocratizingmedicalllms,
      title={Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts}, 
      author={Guorui Zheng and Xidong Wang and Juhao Liang and Nuo Chen and Yuping Zheng and Benyou Wang},
      year={2024},
      eprint={2410.10626},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2410.10626}, 
}