Jihun Yun

jihuny

·

AI & ML interests

Optimization

Recent Activity

new activity 8 days ago

KRAFTON/Raon-1-mini-preview:Raon-mHC VS Deepseek v4.1's Single-pass mHC ?

liked a model 10 days ago

KRAFTON/Raon-1-mini-preview

new activity 13 days ago

KRAFTON/Raon-1-mini-preview:RDA vs Gated DeltaNet 2

View all activity

Organizations

New activity in KRAFTON/Raon-1-mini-preview 8 days ago

Raon-mHC VS Deepseek v4.1's Single-pass mHC ?

#6 opened 8 days ago by

liked a model 10 days ago

KRAFTON/Raon-1-mini-preview

Text Generation • 29B • Updated 9 days ago • 3.93k • 233

New activity in KRAFTON/Raon-1-mini-preview 13 days ago

RDA vs Gated DeltaNet 2

#1 opened 15 days ago by

updated 10 models about 2 months ago

jihuny/qwen2.5-math-7b-numina-grpo-lr5e6-cumkl

jihuny/qwen2.5-math-7b-numina-kraft-b0.1-lr1e6-cumkl

jihuny/phi4-mini-instruct-numina-grpo-lr1e6-cumkl

jihuny/qwen2.5-math-7b-numina-grpo-lr1e6-cumkl

jihuny/llama3.2-3b-instruct-numina-kraft-b1.0-lr1e6-cumkl

jihuny/qwen3-4b-base-numina-grpo-lr1e6-cumkl

jihuny/qwen3-4b-base-numina-grpo-lr3e6-cumkl

jihuny/qwen2.5-math-7b-numina-kraft-b1.0-lr1e6-cumkl

jihuny/llama3.2-3b-instruct-numina-kraft-b0.1-lr1e6-cumkl

jihuny/qwen2.5-math-7b-numina-kraft-b1.0-lr5e6-cumkl

published 7 models about 2 months ago

jihuny/phi4-mini-instruct-numina-kraft-b0.1-lr1e6-cumkl

jihuny/phi4-mini-instruct-numina-kraft-b1.0-lr1e6-cumkl

jihuny/phi4-mini-instruct-numina-grpo-lr1e6-cumkl

jihuny/llama3.2-3b-instruct-numina-kraft-b1.0-lr1e6-cumkl

jihuny/qwen2.5-math-7b-numina-grpo-lr1e6-cumkl

jihuny/qwen2.5-math-7b-numina-kraft-b1.0-lr1e6-cumkl

jihuny/qwen3-4b-base-numina-grpo-lr1e6-cumkl