image/png

Training Details

Others

  • VRAM ์•„์Šฌ์•„์Šฌ (block_size=20000, gradient_accumulation_steps=2 ์ „๋ถ€ CUDA OOM)
  • ๊ณ ์งˆ์ ์ธ "ํ•œ ๋ฒˆ ์ž˜๋ชป ์ƒ๊ฐํ•˜๋ฉด ์ž ๊น๋งŒ์š” ํ•ด๋†“๊ณ ๋„ ๊ณ„์† ๊ฐ™์€ ์‹ค์ˆ˜๋ฅผ ๋ฐ˜๋ณตํ•˜๋Š” ํ˜„์ƒ"์ด ํ•ด๊ฒฐ์ด ์•ˆ๋จ
    • EXAONE์˜ ํŠน์„ฑ or ์†Œํ˜•๋ชจ๋ธ์˜ ํŠน์„ฑ or ๋ฒˆ์—ญ ๋ฐ์ดํ„ฐ์˜ ํŠน์„ฑ
Downloads last month
13
Safetensors
Model size
7.82B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for werty1248/EXAONE-3.5-7.8B-s1.1-Ko-Native

Quantizations
1 model