qutrino
/

7b-finetune

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Edit model card

beomi/open-llama-2-ko-7b 모델을 kyujinpy/KOpen-platypus 로 학습하였습니다.

파인튜닝방법

lora
lora_r: 16
lora_alpha: 16
loca_dropout: 0.05

basemodel

beomi/open-llama-2-ko-7b

instruction dataset

kyujinpy/KOpen-platypus only

Downloads last month: 1,232

Dataset used to train qutrino/7b-finetune