Sft-new ssurface/qwen3-4b-sft-l5-merged 4B • Updated 6 days ago • 20 ssurface/qwen3-4b-sft-l3-merged 4B • Updated 6 days ago • 19 ssurface/qwen3-4b-sft-l4-merged 4B • Updated 6 days ago • 17 ssurface/qwen3-4b-sft-l2-merged 4B • Updated 6 days ago • 17
GRPO no length punshiment SFT GSM8K ssurface/qwen3-4b-grpo-nolength-l1 Text Generation • 4B • Updated 13 days ago • 14 ssurface/qwen3-4b-grpo-nolength-l2 Text Generation • 4B • Updated 13 days ago • 20 ssurface/qwen3-4b-grpo-nolength-l3 Text Generation • 4B • Updated 13 days ago • 21 ssurface/qwen3-4b-grpo-nolength-l4 Text Generation • 4B • Updated 13 days ago • 19
GRPO SFT GSM8K ssurface/qwen3-4b-grpo-l1 Text Generation • 4B • Updated 19 days ago • 19 ssurface/qwen3-4b-grpo-l2 Text Generation • 4B • Updated 19 days ago • 19 ssurface/qwen3-4b-grpo-l3 Text Generation • 4B • Updated 19 days ago • 24 ssurface/qwen3-4b-grpo-l4 Text Generation • 4B • Updated 19 days ago • 18
GRPO SFT-Length-Punishment-GDPO SFT GSM8K ssurface/qwen3-4b-gdpo-length-sft-l1 Text Generation • 4B • Updated 12 days ago • 257 ssurface/qwen3-4b-gdpo-length-sft-l2 Text Generation • 4B • Updated 12 days ago • 258 ssurface/qwen3-4b-gdpo-length-sft-l3 Text Generation • 4B • Updated 12 days ago • 258 ssurface/qwen3-4b-gdpo-length-sft-l4 Text Generation • 4B • Updated 12 days ago • 267
GRPO abstract reward SFT GSM8K ssurface/qwen3-4b-grpo-abstract-l1 Text Generation • 4B • Updated 15 days ago • 25 ssurface/qwen3-4b-grpo-abstract-l2 Text Generation • 4B • Updated 15 days ago • 24 ssurface/qwen3-4b-grpo-abstract-l3 Text Generation • 4B • Updated 15 days ago • 25 ssurface/qwen3-4b-grpo-abstract-l4 Text Generation • 4B • Updated 15 days ago • 25
Qwen3-4B CoT Compression Study LoRA adapters trained for 5 progressively shorter chain-of-thought styles on GSM8K, plus the eval artifacts behind the Pareto curve. ssurface/qwen3-4b-cot-compress-l1 Text Generation • Updated May 25 • 17 ssurface/qwen3-4b-cot-compress-l2 Text Generation • Updated May 25 • 5 ssurface/qwen3-4b-cot-compress-l3 Text Generation • Updated May 25 • 4 ssurface/qwen3-4b-cot-compress-l4 Text Generation • Updated May 25 • 3
Sft-new ssurface/qwen3-4b-sft-l5-merged 4B • Updated 6 days ago • 20 ssurface/qwen3-4b-sft-l3-merged 4B • Updated 6 days ago • 19 ssurface/qwen3-4b-sft-l4-merged 4B • Updated 6 days ago • 17 ssurface/qwen3-4b-sft-l2-merged 4B • Updated 6 days ago • 17
GRPO SFT-Length-Punishment-GDPO SFT GSM8K ssurface/qwen3-4b-gdpo-length-sft-l1 Text Generation • 4B • Updated 12 days ago • 257 ssurface/qwen3-4b-gdpo-length-sft-l2 Text Generation • 4B • Updated 12 days ago • 258 ssurface/qwen3-4b-gdpo-length-sft-l3 Text Generation • 4B • Updated 12 days ago • 258 ssurface/qwen3-4b-gdpo-length-sft-l4 Text Generation • 4B • Updated 12 days ago • 267
GRPO no length punshiment SFT GSM8K ssurface/qwen3-4b-grpo-nolength-l1 Text Generation • 4B • Updated 13 days ago • 14 ssurface/qwen3-4b-grpo-nolength-l2 Text Generation • 4B • Updated 13 days ago • 20 ssurface/qwen3-4b-grpo-nolength-l3 Text Generation • 4B • Updated 13 days ago • 21 ssurface/qwen3-4b-grpo-nolength-l4 Text Generation • 4B • Updated 13 days ago • 19
GRPO abstract reward SFT GSM8K ssurface/qwen3-4b-grpo-abstract-l1 Text Generation • 4B • Updated 15 days ago • 25 ssurface/qwen3-4b-grpo-abstract-l2 Text Generation • 4B • Updated 15 days ago • 24 ssurface/qwen3-4b-grpo-abstract-l3 Text Generation • 4B • Updated 15 days ago • 25 ssurface/qwen3-4b-grpo-abstract-l4 Text Generation • 4B • Updated 15 days ago • 25
GRPO SFT GSM8K ssurface/qwen3-4b-grpo-l1 Text Generation • 4B • Updated 19 days ago • 19 ssurface/qwen3-4b-grpo-l2 Text Generation • 4B • Updated 19 days ago • 19 ssurface/qwen3-4b-grpo-l3 Text Generation • 4B • Updated 19 days ago • 24 ssurface/qwen3-4b-grpo-l4 Text Generation • 4B • Updated 19 days ago • 18
Qwen3-4B CoT Compression Study LoRA adapters trained for 5 progressively shorter chain-of-thought styles on GSM8K, plus the eval artifacts behind the Pareto curve. ssurface/qwen3-4b-cot-compress-l1 Text Generation • Updated May 25 • 17 ssurface/qwen3-4b-cot-compress-l2 Text Generation • Updated May 25 • 5 ssurface/qwen3-4b-cot-compress-l3 Text Generation • Updated May 25 • 4 ssurface/qwen3-4b-cot-compress-l4 Text Generation • Updated May 25 • 3
