Hugging Face's logo

medAdapt
/
MedLLaMA-13B-SFT

Question Answering
Safetensors
French
English
llama
medical
instruction-tuning
sft
lora
causal-lm
Model card Files
xet
Community

MedLLaMA-13B-SFT (SFT)

Model description

This checkpoint is a supervised fine-tuned (SFT) version of MedLLaMA-13B, trained on labeled medical QA (MedInjection-FR/ALL) data to improve task performance—especially for medical MCQA. SFT is implemented using DoRA.

Downloads last month
8
Safetensors
Model size
13B params
Tensor type
F32
·
Inference Providers NEW
Question Answering
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train medAdapt/MedLLaMA-13B-SFT