lyx02klmy/qwen3-4b-sums-diffs-grpo-step10
4B • Updated • 5
Liam PRO
lyx02klmy
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
REVES: REvision and VErification--Augmented Training for Test-Time Scaling updated a model about 2 months ago
lyx02klmy/qwen3-4b-sums-diffs-grpo-step10 published a model about 2 months ago
lyx02klmy/qwen3-4b-sums-diffs-grpo-step10Organizations
None yet
lyx02klmy/erdos_qwen3_4b_step20
4B • Updated • 4
lyx02klmy/erdos_qwen3_4b_step15
4B • Updated • 4
lyx02klmy/cp_qwen3_4b_step16
4B • Updated • 2
lyx02klmy/cp_qwen3_4b_step12
4B • Updated • 4
lyx02klmy/cp_qwen3_4b_step8
4B • Updated • 4
lyx02klmy/cp_qwen3_4b_step4
4B • Updated • 3
lyx02klmy/qwen3-4b-sums-diffs-grpo-step1
4B • Updated • 3
lyx02klmy/qwen3-4b-cp26-grpo-v5step2-p60n14
Text Generation • 4B • Updated • 4
lyx02klmy/qwen3-4b-cp26-grpo-v5step1-p60n18
Text Generation • 4B • Updated • 5
lyx02klmy/qwen3-4b-cp26-grpo-2step-bsz40
4B • Updated • 3
lyx02klmy/qwen3-4b-cp26-grpo-1step-bsz128
Text Generation • 4B • Updated • 4
lyx02klmy/qwen3-4b-circle-packing-reinforce-v4-step2
4B • Updated • 4
lyx02klmy/qwen3-4b-circle-packing-reinforce-v3-step2
4B • Updated • 2
lyx02klmy/qwen3-4b-circle-packing-grpo-step4
4B • Updated • 2
lyx02klmy/sft_runs_DeepSeek-R1-Distill-Qwen-1.5B_step3
2B • Updated • 2
lyx02klmy/sft_runs_DeepSeek-R1-Distill-Qwen-7B_one_step
8B • Updated • 2
lyx02klmy/sft_runs_DeepSeek-R1-Distill-Qwen-1.5B_one_step
2B • Updated • 2
lyx02klmy/sft_runs_OpenReasoning-Nemotron-1.5B_one_step
2B • Updated • 2
lyx02klmy/sft_runs_DeepSeek-R1-Distill-Qwen-7B
Updated
lyx02klmy/sft_runs_no_hint_DeepSeek-R1-Distill-Qwen-1.5B
2B • Updated • 1