pfnet/Preferred-MedLLM-Qwen-72B

Model

Preferred-MedLLM-Qwen-72B

13

7 commits

2 linked in READMEs

updated May 11, 2025

See the code

README

Preferred-MedLLM-Qwen-72B

Model Description

Preferred-MedLLM-Qwen-72B is a finetuned model based on Qwen/Qwen2.5-72B, which has undergone continued pretraining on an original corpus of medical-related text.

The model is released under the Qwen LICENSE.

Model Performance

The table below shows the performance on the Japanese medical licensing examination from 2018 to 2022 (IgakuQA).

Model IDAverage20182019202020212022
Preferred-MedLLM-Qwen-72B431.2434420439430433
GPT-4o430.4427431433427434
Qwen2.5-72B398.4412394394393399
Llama3-Preferred-MedSwallow-70B395.2407390391393395
GPT-4388.8382385387398392
Mistral-Large-Instruct-2407376370371390373376
Llama-3.1-Swallow-70B-v0.1368.4379378379351355
Meta-Llama-3-70B334.6353340348314318
GPT-3.5273.2266250266297287

Limitations

The model was developed for research purposes and is not intended for clinical diagnosis. It is the users' responsibility to ensure compliance with applicable rules and regulations.

Contributors

Preferred Networks, Inc.

  • Junichiro Iwasawa
  • Wataru Kawakami
  • Keita Suzuki

Publications

Detailed evaluation results are given in the blog and research paper.

Citations

@article{preferredmedllm2025,
      title={Stabilizing Reasoning in Medical LLMs with Continued Pretraining and Reasoning Preference Optimization}, 
      author={Kawakami, Wataru and Suzuki, Keita and Iwasawa, Junichiro},
      journal={arXiv preprint arXiv:2504.18080},
      year={2025}
}

License

Qwen LICENSE

endpoints_compatible
safetensors
text-generation
transformers

Contributors

jiwasawa

6 commits

pfnet/Preferred-MedLLM-Qwen-72B

Model

Preferred-MedLLM-Qwen-72B

13

7 commits

2 linked in READMEs

updated May 11, 2025

See the code

README

Preferred-MedLLM-Qwen-72B

Model Description

Preferred-MedLLM-Qwen-72B is a finetuned model based on Qwen/Qwen2.5-72B, which has undergone continued pretraining on an original corpus of medical-related text.

The model is released under the Qwen LICENSE.

Model Performance

The table below shows the performance on the Japanese medical licensing examination from 2018 to 2022 (IgakuQA).

Model IDAverage20182019202020212022
Preferred-MedLLM-Qwen-72B431.2434420439430433
GPT-4o430.4427431433427434
Qwen2.5-72B398.4412394394393399
Llama3-Preferred-MedSwallow-70B395.2407390391393395
GPT-4388.8382385387398392
Mistral-Large-Instruct-2407376370371390373376
Llama-3.1-Swallow-70B-v0.1368.4379378379351355
Meta-Llama-3-70B334.6353340348314318
GPT-3.5273.2266250266297287

Limitations

The model was developed for research purposes and is not intended for clinical diagnosis. It is the users' responsibility to ensure compliance with applicable rules and regulations.

Contributors

Preferred Networks, Inc.

  • Junichiro Iwasawa
  • Wataru Kawakami
  • Keita Suzuki

Publications

Detailed evaluation results are given in the blog and research paper.

Citations

@article{preferredmedllm2025,
      title={Stabilizing Reasoning in Medical LLMs with Continued Pretraining and Reasoning Preference Optimization}, 
      author={Kawakami, Wataru and Suzuki, Keita and Iwasawa, Junichiro},
      journal={arXiv preprint arXiv:2504.18080},
      year={2025}
}

License

Qwen LICENSE

endpoints_compatible
safetensors
text-generation
transformers

Contributors

jiwasawa

6 commits