Caveman Reasoning Compression Compressed (caveman) reasoning traces train models to reason in ~2-3x fewer tokens at equal or better accuracy. For full ablation: sibling collection. marcodsn/gemma-4-12b-it-flint-section-merged Text Generation • 12B • Updated 2 days ago • 3 marcodsn/gemma-4-12b-it-flint-section Text Generation • Updated 2 days ago marcodsn/qwen3.5-4b-sft-flint-section-v2-nosys Text Generation • Updated 2 days ago marcodsn/qwen3.5-4b-sft-flint-section-v2-flintsys Text Generation • Updated 2 days ago
Reasoning Compression: Ablation Arms All ablation arms + dataset variants behind the caveman reasoning-compression study. For headline artifacts: see the main collection. marcodsn/qwen3.5-4b-sft-crucible-v2 Text Generation • Updated 2 days ago marcodsn/gemma-4-12b-it-sft-crucible Text Generation • Updated 2 days ago marcodsn/qwen3.5-4b-sft-flint-section-v2 Text Generation • Updated 2 days ago marcodsn/qwen3.5-4b-sft-flint-mixed-v2 Text Generation • Updated 2 days ago
Caveman Reasoning Compression Compressed (caveman) reasoning traces train models to reason in ~2-3x fewer tokens at equal or better accuracy. For full ablation: sibling collection. marcodsn/gemma-4-12b-it-flint-section-merged Text Generation • 12B • Updated 2 days ago • 3 marcodsn/gemma-4-12b-it-flint-section Text Generation • Updated 2 days ago marcodsn/qwen3.5-4b-sft-flint-section-v2-nosys Text Generation • Updated 2 days ago marcodsn/qwen3.5-4b-sft-flint-section-v2-flintsys Text Generation • Updated 2 days ago
Reasoning Compression: Ablation Arms All ablation arms + dataset variants behind the caveman reasoning-compression study. For headline artifacts: see the main collection. marcodsn/qwen3.5-4b-sft-crucible-v2 Text Generation • Updated 2 days ago marcodsn/gemma-4-12b-it-sft-crucible Text Generation • Updated 2 days ago marcodsn/qwen3.5-4b-sft-flint-section-v2 Text Generation • Updated 2 days ago marcodsn/qwen3.5-4b-sft-flint-mixed-v2 Text Generation • Updated 2 days ago