EpistemeAI/Reasoning-Medical0.1-27B
Image-Text-to-Text • 28B • Updated
Thomas Yiu
legolasyiu
AI & ML interests
Superalignment , alignment, safety LLM, AI, AGI, ASI.
Donation/Funding
https://account.venmo.com/u/Thomas-Yiu
Recent Activity
updated a model 24 minutes ago
EpistemeAI/Reasoning-Medical0.1-27B published a model 24 minutes ago
EpistemeAI/Reasoning-Medical0.1-27B updated a dataset about 6 hours ago
EpistemeAI/medical-reasoning-mix-100kOrganizations
updated a
model 24 minutes ago
published a
model 24 minutes ago
updated a
dataset about 6 hours ago
published a
dataset about 6 hours ago
updated a
model about 10 hours ago
published a
model about 10 hours ago
liked 2
models about 15 hours ago
updated 2
models about 19 hours ago
updated a
model 1 day ago
published a
model 1 day ago
updated a
model 1 day ago
liked a
dataset 1 day ago
liked a
model 2 days ago
published a
model 2 days ago
posted an update 2 days ago
Post
78
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
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 |updated a
model 2 days ago
updated a
bucket 3 days ago
published a
bucket 3 days ago