Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
legolasyiu 
posted an update Jun 18
Post
196
Introducing Reasoning-Medical-27B is designed for advanced medical reasoning in professional medicine, medical genetics, college biology/medicine, and clinical knowledge. The model was fine-tuned on a large-scale dataset of 370,000 high-quality question-and-answer examples, incorporating Chain-of-Thought reasoning to improve step-by-step problem solving. Training was performed using the GRPO trainer with the Unsloth optimization method for efficient fine-tuning.
MedQA: 93% vs MedGemma 85.3%

Model: EpistemeAI/Reasoning-Medical-27B



# Benchmark

| Task              | Version | Filter         | n-shot | Metric      | Direction | Reasoning Medical 27B | Qwen 3.6 27B | MedGemma 1 27B |
|-------------------|--------:|----------------|-------:|-------------|:---------:|----------------------:|-------------:|----------------:|
| MMLU-Pro Biology  | 3.1     | custom-extract | 2      | exact_match | ↑         | 0.85                  | —            | —               |
| MMLU-ProX Biology | 0       | custom-extract | 2      | exact_match | ↑         | 0.80                  | —            | —               |
| MedQA             | YAML    | none           | 2      | acc         | ↑         | 0.93                  | 0.844        | 0.853           |
CatHouseDev

Hey! As an RN and local llm I love this project! Is there any chance of you putting out a GGUF?

·
legolasyiu

Hi, nice to meet you.

Yes, here is the lists of gguf you can download for your project:

https://huggingface.co/models?other=base_model:quantized:EpistemeAI/Reasoning-Medical-27B
legolasyiu
•
edited 9 days ago

HealthBench Professional.

The Medical Reasoning model 27B is competitive to Opus 4.8 and GPT 5.5.

Task Version Filter n-shot Metric Direction Reasoning Medical 27B Opus 4.8 GPT 5.5 Kimi-K2.6
HealthBench Professional none none none acc ↑ 0.56 0.512 0.518 0.503

output

·
legolasyiu
•
edited 2 days ago

We release the EpistemeAI/Reasoning-Medical0.1-E4B-sft is designed for advanced medical reasoning in professional medicine, medical genetics, college biology/medicine, and clinical knowledge. It was traing using superised fine tuning techniques(sft).

MedQA scores: 76.0 which outscores previous Medical models.

medqa_benchmark_chart

Reasoning-Medical0.1-E4B-sft achieved an 87.5/100 mean BioSafeBench score and an 85% automatic pass rate across 40 biological-safety evaluations. The model scored 100% on benign biological questions and bounded dual-use responses, 75% on refusal-and-redirection cases, and 50% on ambiguous requests requiring clarification and safety limitations. These heuristic results require human review and should not be interpreted as a formal safety certification.
https://github.com/AIEpisteme/BioSafeBench

thank you to Unsloth for their training code.
In this post