RichardErkhov/FreedomIntelligence_-_Apollo-2B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Apollo-2B - GGUF

• Model creator: https://huggingface.co/FreedomIntelligence/
• Original model: https://huggingface.co/FreedomIntelligence/Apollo-2B/

Name	Quant method	Size
Apollo-2B.Q2_K.gguf	Q2_K	1.08GB
Apollo-2B.IQ3_XS.gguf	IQ3_XS	1.16GB
Apollo-2B.IQ3_S.gguf	IQ3_S	1.2GB
Apollo-2B.Q3_K_S.gguf	Q3_K_S	1.2GB
Apollo-2B.IQ3_M.gguf	IQ3_M	1.22GB
Apollo-2B.Q3_K.gguf	Q3_K	1.29GB
Apollo-2B.Q3_K_M.gguf	Q3_K_M	1.29GB
Apollo-2B.Q3_K_L.gguf	Q3_K_L	1.36GB
Apollo-2B.IQ4_XS.gguf	IQ4_XS	1.4GB
Apollo-2B.Q4_0.gguf	Q4_0	1.44GB
Apollo-2B.IQ4_NL.gguf	IQ4_NL	1.45GB
Apollo-2B.Q4_K_S.gguf	Q4_K_S	1.45GB
Apollo-2B.Q4_K.gguf	Q4_K	1.52GB
Apollo-2B.Q4_K_M.gguf	Q4_K_M	1.52GB
Apollo-2B.Q4_1.gguf	Q4_1	1.56GB
Apollo-2B.Q5_0.gguf	Q5_0	1.68GB
Apollo-2B.Q5_K_S.gguf	Q5_K_S	1.68GB
Apollo-2B.Q5_K.gguf	Q5_K	1.71GB
Apollo-2B.Q5_K_M.gguf	Q5_K_M	1.71GB
Apollo-2B.Q5_1.gguf	Q5_1	1.79GB
Apollo-2B.Q6_K.gguf	Q6_K	1.92GB
Apollo-2B.Q8_0.gguf	Q8_0	2.49GB

Original model description:

license: apache-2.0

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

• [2024.03.07] 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-0.5B-GGUF • 🤗 Apollo-2B-GGUF • 🤗 Apollo-6B-GGUF • 🤗 Apollo-7B-GGUF

Usage Format

User:{query}\nAssistant:{response}<|endoftext|>

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

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}
}