Edit model card

Model Card for Model ID

chat-vector ๋…ผ๋ฌธ( https://arxiv.org/abs/2310.04799v2 )์— ๊ทผ๊ฑฐํ•˜์—ฌ,

llama3์˜ pre-trained ๋ชจ๋ธ์˜ parameter์™€ instruction ๋ชจ๋ธ์˜ ๋งค๊ฐœ๋ณ€์ˆ˜์˜ ์ฐจ์ด๋ฅผ

beomi๋‹˜์˜ Llama-3-Open-Ko-8B์— ์ ์šฉํ•œ ๋ชจ๋ธ

maywell๋‹˜์˜ ์ด ๋ฐฉ๋ฒ•๋ก ( https://huggingface.co/blog/maywell/llm-feature-transfer )์„ ๋ฐ›์•„๋“ค์—ฌ ๊ฐ€์ค‘์น˜ ์—…๋ฐ์ดํŠธ

64GB์˜ ram ์‹œ์Šคํ…œ ํ•˜์—์„œ ์ง„ํ–‰ํ•˜๋‹ค๋ณด๋‹ˆ, ์ž๋ฃŒํ˜•์„ bf16ํ˜•ํƒœ๋กœ ์ง„ํ–‰ํ•˜์˜€์Œ

Metric

results/all/aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec

0 5 10
kobest_boolq (macro_f1) 0.64898 0.603325 0.575417
kobest_copa (macro_f1) 0.682517 0.706718 0.693293
kobest_hellaswag (macro_f1) 0.42651 0.391038 0.386523
kobest_sentineg (macro_f1) 0.501351 0.861108 0.876122
kohatespeech (macro_f1) 0.252714 0.330103 0.305009
kohatespeech_apeach (macro_f1) 0.337667 0.536842 0.526639
kohatespeech_gen_bias (macro_f1) 0.124535 0.512855 0.457998
korunsmile (f1) 0.358703 0.330155 0.32824
nsmc (acc) 0.59726 0.75206 0.74702
pawsx_ko (acc) 0.5195 0.513 0.4805

Used Model

  • Base model(weight diff๋ฅผ ๊ตฌํ•˜๊ธฐ ์œ„ํ•œ ๋ฒ ์ด์Šค ๋ชจ๋ธ) : meta-llama/Meta-Llama-3-8B
  • Chat model(weight diff๋ฅผ ์ œ๊ณตํ•˜๋Š” instruction model) : meta-llama/Meta-Llama-3-8B-Instruct
  • Target model(weight diff๋ฅผ ์ ์šฉํ•ด์„œ instruction ํŠ ์„ ํ•˜๊ณ ์ž ํ•˜๋Š” ๋ชจ๋ธ) : beomi/Llama-3-Open-Ko-8B
Downloads last month
1
Safetensors
Model size
8.03B params
Tensor type
BF16
ยท