JingwenGu/qwen3-4b-online-sft
4B • Updated • 27
Jingwen Gu
JingwenGu
AI & ML interests
None yet
Recent Activity
updated a model 1 minute ago
JingwenGu/qwen3-4b-online-sft updated a model about 10 hours ago
JingwenGu/qwen3-1.7b-sft-grpo-steps500to1000-epoch2 published a model about 10 hours ago
JingwenGu/qwen3-1.7b-sft-grpo-steps500to1000-epoch2Organizations
None yet
JingwenGu/qwen3-1.7b-sft-grpo-steps500to1000-epoch2
2B • Updated
JingwenGu/qwen3-1.7b-sft-steps750to1000-epoch2
2B • Updated
JingwenGu/qwen3-1.7b-sft-steps500to1000-epoch2
2B • Updated • 12
JingwenGu/qwen3-1.7b-maxrl-lr5e-7-step900
2B • Updated • 14
JingwenGu/qwen3-1.7b-maxrl-lr5e-7-step800
2B • Updated • 13
JingwenGu/qwen3-1.7b-maxrl-lr5e-7-step700
2B • Updated • 15
JingwenGu/qwen3-1.7b-maxrl-lr5e-7-step600
2B • Updated • 16
JingwenGu/qwen3-1.7b-maxrl-lr5e-7-step500
2B • Updated • 16
JingwenGu/qwen3-1.7b-maxrl-lr5e-7-step400
2B • Updated • 17
JingwenGu/qwen3-1.7b-maxrl-lr5e-7-step300
2B • Updated • 15
JingwenGu/qwen3-1.7b-maxrl-lr5e-7-step200
2B • Updated • 16
JingwenGu/qwen3-1.7b-sft-grpo-steps750to1000
2B • Updated • 15
JingwenGu/maxrl_merged_math_knk_0.25
2B • Updated • 11
JingwenGu/qwen3-1.7b-sft-grpo-steps500to1000
2B • Updated • 19
JingwenGu/maxrl_merged_math_knk_taskarith
2B • Updated • 17
JingwenGu/maxrl_merged_math_knk_ties20
2B • Updated • 17
JingwenGu/maxrl_merged_math_knk_0.75
2B • Updated • 17
JingwenGu/maxrl_merged_math_knk_0.5
2B • Updated • 17
JingwenGu/qwen3-1.7b-sft-steps750to1000-fsdp-raw
Updated
JingwenGu/qwen3-1.7b-sft-steps750to1000
2B • Updated • 18
JingwenGu/qwen3-1.7b-sft-steps500to1000-fsdp-raw
Updated
JingwenGu/qwen3-1.7b-sft-steps500to1000
2B • Updated • 30
JingwenGu/qwen3-1.7b-base-steps50to100-epoch3
2B • Updated • 31
JingwenGu/qwen3-1.7b-maxrl-lr5e-7-step100
2B • Updated • 22
JingwenGu/qwen3-1.7b-base-steps50to100-epoch2
2B • Updated • 29
JingwenGu/qwen3-1.7b-maxrl-correct-continue-step1000
2B • Updated • 18
JingwenGu/qwen3-1.7b-maxrl-correct-continue-step900
2B • Updated • 20
JingwenGu/qwen3-1.7b-maxrl-correct-continue-step800
2B • Updated • 17
JingwenGu/qwen3-1.7b-maxrl-correct-continue-step700
2B • Updated • 19