Sleeping
Agents
Trl Trackio
🚀
Jihun Yun
jihuny
·
AI & ML interests
Optimization
Recent Activity
new activity about 4 hours ago
KRAFTON/Raon-1-mini-preview:RDA vs Gated DeltaNet 2 updated a model about 2 months ago
jihuny/qwen2.5-math-7b-numina-grpo-lr5e6-cumkl updated a model about 2 months ago
jihuny/qwen2.5-math-7b-numina-kraft-b0.1-lr1e6-cumklOrganizations
models 64
jihuny/qwen2.5-math-7b-numina-grpo-lr1e6-cumkl
Updated
jihuny/llama3.2-3b-instruct-numina-kraft-b0.1-lr1e6-cumkl
Updated
jihuny/phi4-mini-instruct-numina-grpo-lr3e6-cumkl
Updated
jihuny/qwen2.5-math-7b-numina-kraft-b1.0-lr5e6-cumkl
Updated
jihuny/llama3.2-3b-instruct-numina-kraft-b1.0-lr1e6-cumkl
Updated
jihuny/qwen2.5-math-7b-numina-kraft-b0.1-lr1e6-cumkl
Updated
jihuny/qwen3-4b-base-numina-grpo-lr1e6-cumkl
Updated
jihuny/phi4-mini-instruct-numina-kraft-b1.0-lr5e6-cumkl
Updated
jihuny/phi4-mini-instruct-numina-grpo-lr1e6-cumkl
Updated
jihuny/qwen3-4b-base-numina-grpo-lr5e6-cumkl
Updated
datasets 934
jihuny/tldr-preference
Viewer • Updated • 179k • 7
jihuny/tldr-reference
Viewer • Updated • 130k • 9
jihuny/fineweb-100bt-tokenized
Updated • 18
jihuny/beyond_rlhf_uf_1024_final
Viewer • Updated • 57k • 17
jihuny/beyond_rlhf_uf_1024_ref
Viewer • Updated • 57k • 9
jihuny/beyond_rlhf_uf_1024
Viewer • Updated • 57k • 14
jihuny/llama_uf_10k_armo_s005_dpo_newton
Viewer • Updated • 10k • 7
jihuny/llama_shp_10k_armo_s005_dpo_newton
Viewer • Updated • 10k • 5
jihuny/llama_mag_10k_armo_s005_dpo_newton
Viewer • Updated • 10k • 5
jihuny/llama_arena_10k_armo_s005_dpo_newton
Viewer • Updated • 10k • 7