Text Generation
PEFT
Safetensors
English
Croatian
medgemma
medical
clinical-error-detection
patient-safety
lora
sft
emergency-medicine
internal-medicine
conversational
Eval Results (legacy)
Instructions to use Vrda/medgemma-27b-clinical-error-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Vrda/medgemma-27b-clinical-error-sft with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("google/medgemma-27b-it") model = PeftModel.from_pretrained(base_model, "Vrda/medgemma-27b-clinical-error-sft") - Notebooks
- Google Colab
- Kaggle
add Krabic et al. 2026 citation
Browse files
README.md
CHANGED
|
@@ -238,6 +238,17 @@ If you use this model, please cite:
|
|
| 238 |
year={2026},
|
| 239 |
url={https://github.com/IvanLuksic/medgemma-next}
|
| 240 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 241 |
```
|
| 242 |
|
| 243 |
## License
|
|
|
|
| 238 |
year={2026},
|
| 239 |
url={https://github.com/IvanLuksic/medgemma-next}
|
| 240 |
}
|
| 241 |
+
|
| 242 |
+
@article{krabic2026llm,
|
| 243 |
+
title={Large language models as second reviewers for medical errors in real-world internal medicine reports: a prospective comparative study of open- and closed-source models},
|
| 244 |
+
author={Krabic, R. and Viculin, I. and Boban, Z. and Kumric, M. and Vilovic, M. and Vrdoljak, J. and Bozic, J.},
|
| 245 |
+
journal={International Journal of Medical Informatics},
|
| 246 |
+
volume={211},
|
| 247 |
+
pages={106316},
|
| 248 |
+
year={2026},
|
| 249 |
+
doi={10.1016/j.ijmedinf.2026.106316},
|
| 250 |
+
pmid={41655522}
|
| 251 |
+
}
|
| 252 |
```
|
| 253 |
|
| 254 |
## License
|