리더보드 체크용입니다.

Llama-3.2-1B-Instruct 모델을 한국어 instruction dataset 1K로 LoRA finetuning을 진행했습니다.

This model is just for testing uploads to the leaderboard. 😅

We fine-tuned the Llama-3.2-1B-Instruct model on a Korean instruction dataset containing 1,000 samples using LoRA (Unsloth).

Safetensors

Model size

1.24B params

Tensor type

BF16

Inference API

Unable to determine this model's library. Check the docs .

Model tree for Yebin46/llama1B

Base model

Finetuned

(152)

this model

Yebin46
/

llama1B