AlienKevin/marin-8b-tb2-eval-traces download history
AlienKevin/marin-8b-tb2-eval-traces is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 51 times (13 in the last 7 days), and 254 times in total. It ranks #182,934 among datasets by monthly downloads.
Marin-8B Terminal-Bench 2.0 Eval Traces Per-trial agent trajectories from running Terminal-Bench 2.0 against: marin_8b_base — marin-community/marin-8b-instruct (base, no SFT). 0 / 89 = 0.0% unique solves (89 canonical trials). marin_8b_sft_step5720 — exp4420 SFT (Marin-8B Instruct + 366K