10 LoRA adapters + 6 datasets. Algo template SFT vs QwQ distillation on Qwen2.5-1.5B-Instruct across 4 reasoning domains.
Reasoning Degeneration Dev
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
models 10
reasoning-degeneration-dev/algo-sft-long-arithmetic-distill-qwq
Updated
reasoning-degeneration-dev/algo-sft-long-arithmetic-chunked
Updated • 4
reasoning-degeneration-dev/algo-sft-long-arithmetic-standard
Updated • 2
reasoning-degeneration-dev/algo-sft-formal-logic-distill-qwq
Updated • 2
reasoning-degeneration-dev/algo-sft-formal-logic-truth-table
Updated
reasoning-degeneration-dev/algo-sft-formal-logic-bottom-up
Updated • 1
reasoning-degeneration-dev/algo-sft-conlang-morphology-distill-qwq
Updated • 4
reasoning-degeneration-dev/algo-sft-conlang-morphology-ordered-rules-d5d7
Updated • 1
reasoning-degeneration-dev/algo-sft-cellular-automata-distill-qwq
Updated • 1
reasoning-degeneration-dev/algo-sft-cellular-automata-step-simulation-d5
Updated
datasets 576
reasoning-degeneration-dev/PROJECT-MANIFEST
Viewer • Updated • 537 • 15
reasoning-degeneration-dev/ttt-discover-circle_packing_26-qwen3-8b-v2
Viewer • Updated • 24 • 22
reasoning-degeneration-dev/ttt-discover-circle_packing_26-qwen3-8b-v1
Viewer • Updated • 20 • 28 • 1
reasoning-degeneration-dev/ttt-discover-circle_packing_24-qwen3-8b
Viewer • Updated • 19 • 12
reasoning-degeneration-dev/RESEARCH_DASHBOARD
Updated • 93
reasoning-degeneration-dev/algorithmic-sft-full-eval-v3
Viewer • Updated • 50 • 18
reasoning-degeneration-dev/multiplex-countdown-val-responses-v2
Updated • 3
reasoning-degeneration-dev/sdc-lenient-chart-v1
Viewer • Updated • 1 • 16
reasoning-degeneration-dev/sdc-strict-vs-lenient-v1
Viewer • Updated • 75 • 17
reasoning-degeneration-dev/sdc-final-gradient-v1
Viewer • Updated • 1 • 15