mhseo2/sft_qwen3base8b_qwen3moe30b_ot3_n53105-step250
8B • Updated • 16
Minhyuk Seo
mhseo2
AI & ML interests
None yet
Recent Activity
updated a model about 1 hour ago
mhseo2/sft_olmo3base7b_amr1_0528_math_n204800-step800 published a model about 1 hour ago
mhseo2/sft_olmo3base7b_amr1_0528_math_n204800-step800 updated a model about 1 hour ago
mhseo2/opd_olmo3_7b_thinksft_olmo3_7b_think_ot3math-step100Organizations
None yet
mhseo2/sft_qwen3base8b_qwen3moe30b_deepmath_n57012-step500
8B • Updated • 15
mhseo2/sft_qwen3base8b_qwen3moe30b_deepmath_n57012-step250
8B • Updated • 14
mhseo2/sft_qwen3base8b_qwen3moe30b_deepmath_n57012_lr2e-5-step500
8B • Updated • 15
mhseo2/sft_qwen3base8b_qwen3moe30b_deepmath_n57012_lr2e-5-step250
8B • Updated • 16
mhseo2/sft_qwen3base8b_qwen3moe30b_deepmath_n57012_ep15-step500
8B • Updated • 17
mhseo2/sft_qwen3base8b_qwen3moe30b_deepmath_n57012_ep15-step250
8B • Updated • 19
mhseo2/sft_qwen3base8b_qwen3moe30b_deepmath_n57012_ep15-step2000
8B • Updated • 16
mhseo2/sft_qwen3base8b_qwen3moe30b_deepmath_n57012_ep15-step1500
8B • Updated • 18
mhseo2/sft_qwen3base8b_qwen3moe30b_deepmath_n57012_ep15-step1000
8B • Updated • 15
mhseo2/sft_qwen3base8b_qwen3moe30b_deepmath_n57012_ep15_lr2e-5-step500
8B • Updated • 20
mhseo2/sft_qwen3base8b_qwen3moe30b_deepmath_n57012_ep15_lr2e-5-step250
8B • Updated • 17
mhseo2/sft_qwen3base8b_qwen3moe30b_deepmath_n57012_ep15_lr2e-5-step1500
8B • Updated • 18
mhseo2/sft_qwen3base8b_qwen3moe30b_deepmath_n57012_ep15_lr2e-5-step1000
8B • Updated • 18
mhseo2/sft_qwen3base4b_qwen3moe30b_ot3_n53105-step489
4B • Updated • 15
mhseo2/sft_qwen3base4b_qwen3moe30b_deepmath_n57012-step500
4B • Updated • 14
mhseo2/Qwen3-4B-Inst-Math-Reasoning-SFT-opd
Text Generation • 4B • Updated • 415
mhseo2/Qwen3-8B-Base-opd
Text Generation • 8B • Updated • 419
mhseo2/Qwen3-8B-Base-OT3Math-SFT-step500
Text Generation • 8B • Updated • 411
mhseo2/Qwen3-8B-Base-OT3Math-SFT-step750
Text Generation • 8B • Updated • 413
mhseo2/Qwen3-8B-Base-OT3Math-SFT-step250
Text Generation • 8B • Updated • 419
mhseo2/Qwen3-8B-Base-DeepMath-SFT-step750-eosfix
8B • Updated • 18
mhseo2/Qwen3-8B-Base-DeepMath-SFT-step500-eosfix
8B • Updated • 16
mhseo2/Qwen3-8B-Base-DeepMath-SFT-step250-eosfix
8B • Updated • 27
mhseo2/Qwen3-4B-Base-opd
Text Generation • 4B • Updated • 395
mhseo2/Qwen3-1.7B-Base-opd
Text Generation • 2B • Updated • 398
mhseo2/Qwen3-4B
4B • Updated • 25
mhseo2/Qwen3-4B-OT3-2ep-opd
Text Generation • 4B • Updated • 386
mhseo2/Klear-Reasoner-8B
8B • Updated • 26
mhseo2/Klear-Reasoner-8B-SFT
8B • Updated • 22