FreedomIntelligence / Apollo-MedJamba

huggingface.co
Total runs: 73
24-hour runs: 0
7-day runs: 2
30-day runs: 19
Model's Last Updated: April 25 2024
text-generation

Introduction of Apollo-MedJamba

Model Details of Apollo-MedJamba

MedJamba

Multilingual Medical Model Based On Jamba

👨🏻‍💻 Github •📃 Paper

Apollo

🌈 Update
  • [2024.04.25] MedJamba Model 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

Apollo

Dataset & Evaluation
  • Dataset 🤗 ApolloCorpus

    Click to expand

    Apollo

    • 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:

    • 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
  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

    • Multi Nodes refer to ./scripts/multi_node_train_*.sh
    pip install causal-conv1d>=1.2.0
    pip install mamba-ssm
    

    Node 0:

    bash ./scripts/3.multinode_train_jamba_rank0.sh
    

    ... Node 4:

    bash ./scripts/3.multinode_train_jamba_rank4.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'
    
To do
  • Long Context Capability Evaluation and new Long-Med Benchmark
Acknowledgment
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}
}

Runs of FreedomIntelligence Apollo-MedJamba on huggingface.co

73
Total runs
0
24-hour runs
-3
3-day runs
2
7-day runs
19
30-day runs

More Information About Apollo-MedJamba huggingface.co Model

More Apollo-MedJamba license Visit here:

https://choosealicense.com/licenses/apache-2.0

Apollo-MedJamba huggingface.co

Apollo-MedJamba huggingface.co is an AI model on huggingface.co that provides Apollo-MedJamba's model effect (), which can be used instantly with this FreedomIntelligence Apollo-MedJamba model. huggingface.co supports a free trial of the Apollo-MedJamba model, and also provides paid use of the Apollo-MedJamba. Support call Apollo-MedJamba model through api, including Node.js, Python, http.

FreedomIntelligence Apollo-MedJamba online free

Apollo-MedJamba huggingface.co is an online trial and call api platform, which integrates Apollo-MedJamba's modeling effects, including api services, and provides a free online trial of Apollo-MedJamba, you can try Apollo-MedJamba online for free by clicking the link below.

FreedomIntelligence Apollo-MedJamba online free url in huggingface.co:

https://huggingface.co/FreedomIntelligence/Apollo-MedJamba

Apollo-MedJamba install

Apollo-MedJamba is an open source model from GitHub that offers a free installation service, and any user can find Apollo-MedJamba on GitHub to install. At the same time, huggingface.co provides the effect of Apollo-MedJamba install, users can directly use Apollo-MedJamba installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Apollo-MedJamba install url in huggingface.co:

https://huggingface.co/FreedomIntelligence/Apollo-MedJamba

Url of Apollo-MedJamba

Provider of Apollo-MedJamba huggingface.co

FreedomIntelligence
ORGANIZATIONS

Other API from FreedomIntelligence