Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/FreedomIntelligence/Apollo

Multilingual Medicine: Model, Dataset, Benchmark, Code
https://github.com/FreedomIntelligence/Apollo

llm medical open-source

Last synced: about 2 months ago
JSON representation

Multilingual Medicine: Model, Dataset, Benchmark, Code

Awesome Lists containing this project

README

        

# Multilingual Medicine: Model, Dataset, Benchmark, Code

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


πŸ“ƒ Paper β€’ 🌐 Demo β€’ πŸ€— ApolloCorpus β€’ πŸ€— XMedBench β€’ 🌐 ApolloMoE

δΈ­ζ–‡ | English

![Apollo](assets/apollo_medium_final.png)

## 🌈 Update

* **[2024.10.15]** [ApolloMoE](https://github.com/FreedomIntelligence/ApolloMoE) repo released, covering 50 Languages.
* **[2024.04.25]** [MedJamba](https://huggingface.co/FreedomIntelligence/Apollo-MedJamba) released, train and evaluation code refer to [repo](https://github.com/FreedomIntelligence/MedJamba).
* **[2024.03.07]** [Paper](https://arxiv.org/abs/2403.03640) released.
* **[2024.02.12]** ApolloCorpus and XMedBench is publishedοΌπŸŽ‰
* **[2024.01.23]** Apollo repo is publishedοΌπŸŽ‰

## Results
πŸ€— Apollo-0.5B β€’ πŸ€— Apollo-1.8B β€’ πŸ€— Apollo-2B β€’ πŸ€— Apollo-6B β€’ πŸ€— Apollo-7B β€’ πŸ€— Apollo-34B β€’ πŸ€— Apollo-72B

πŸ€— MedJamba

πŸ€— Apollo-0.5B-GGUF β€’ πŸ€— Apollo-2B-GGUF β€’ πŸ€— Apollo-6B-GGUF β€’ πŸ€— Apollo-7B-GGUF



![Apollo](assets/result.png)

## Usage Format

- 0.5B, 1.8B, 2B, 6B, 7B: User:{query}\nAssistant:{response}<|endoftext|>
- 34B, 72B: <|User|>:{query}\n<|Assistant|>:{response}<|endoftext|>

## Dataset & Evaluation

- Dataset
πŸ€— ApolloCorpus

Click to expand

![Apollo](assets/dataset.png)

- [Zip File](https://huggingface.co/datasets/FreedomIntelligence/ApolloCorpus/blob/main/ApolloCorpus.zip)
- [Data category](https://huggingface.co/datasets/FreedomIntelligence/ApolloCorpus/tree/main/train)
- 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
πŸ€—
XMedBench

Click to expand

- EN:
- [MedQA-USMLE](https://huggingface.co/datasets/GBaker/MedQA-USMLE-4-options)
- [MedMCQA](https://huggingface.co/datasets/medmcqa/viewer/default/test)
- [PubMedQA](https://huggingface.co/datasets/pubmed_qa): Because the results fluctuated too much, they were not used in the paper.
- [MMLU-Medical](https://huggingface.co/datasets/cais/mmlu)
- Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine
- ZH:
- [MedQA-MCMLE](https://huggingface.co/datasets/bigbio/med_qa/viewer/med_qa_zh_4options_bigbio_qa/test)
- [CMB-single](https://huggingface.co/datasets/FreedomIntelligence/CMB): Not used in the paper
- Randomly sample 2,000 multiple-choice questions with single answer.
- [CMMLU-Medical](https://huggingface.co/datasets/haonan-li/cmmlu)
- Anatomy, Clinical_knowledge, College_medicine, Genetics, Nutrition, Traditional_chinese_medicine, Virology
- [CExam](https://github.com/williamliujl/CMExam): Not used in the paper
- Randomly sample 2,000 multiple-choice questions

- ES: [Head_qa](https://huggingface.co/datasets/head_qa)
- FR: [Frenchmedmcqa](https://github.com/qanastek/FrenchMedMCQA)
- HI: [MMLU_HI](https://huggingface.co/datasets/FreedomIntelligence/MMLU_Arabic)
- Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine
- AR: [MMLU_Ara](https://huggingface.co/datasets/FreedomIntelligence/MMLU_Hindi)
- 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:

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

```
bash src/proxy-tuning/scripts/eval/proxy_tuning.sh
```
6. Evaluate your model: Generate score for benchmark

```
bash 4.eval.sh
```

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

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

## Acknowledgment

- [HuatuoGPT-II](https://github.com/FreedomIntelligence/HuatuoGPT-II)
- [proxy-tuning](https://github.com/alisawuffles/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





Star History Chart