Import from Oums/SFT-LLama-7b + standardized README

955fdb3 verified 4 months ago

498 Bytes

language:
  - fr
  - en
license: apache-2.0
tags:
  - medical
  - instruction-tuning
  - sft
  - lora
  - causal-lm
  - question-answering
datasets:
  - MedInjection-FR/ALL
base_model: LLama-2-7b-hf
model_type: causal-lm

LLama-2-7b-hf-SFT (SFT)

Model description

This checkpoint is a supervised fine-tuned (SFT) version of LLama-2-7b-hf, trained on labeled medical QA (MedInjection-FR/ALL) data to improve task performance—especially for medical MCQA. SFT is implemented using DoRA.