sdf-twohop Collection Data, evaluations, and LoRA adapters behind https://www.lesswrong.com/posts/CdWbCvKEoK39L3DzK/small-llms-perform-no-cot-two-hop-reasoning-on-synthetic • 3 items • Updated 4 days ago
model-organisms-for-real/olmo-2-0425-1b-wide-dpo-letters-f-all-flipped-out-0.25-downsample-bystanders Updated Feb 19
model-organisms-for-real/olmo-2-0425-1b-wide-dpo-letters-f-all-flipped-out-0.25-downsample-bystanders Updated Feb 19
model-organisms-for-real/olmo-2-0425-1b-preference-mix-letters-f-all-flipped-out-0.25-downsample-bystanders Viewer • Updated Feb 19 • 94.6k • 17