8 shown

datasets

Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.

01haotang /full-nla-aa-step10001.00-eps6text10K<n<100K0 likes47 downloads2y agoHugging Face 02haotang /full-nla-aa-step10001-eps5text10K<n<100K0 likes29 downloads2y agoHugging Face 03tmpmodelsave /type134_step1000tmp07text1K<n<10K0 likes20 downloads2y agoHugging Face 04tmpmodelsave /type12_plus_sftloss_step1000tmp10text1K<n<10K0 likes12 downloads2y agoHugging Face 05juliadollis /bokeh-eval-infer-step10000-kesctabularn<1K0 likes9 downloads1mo agoHugging Face 06tmpmodelsave /type12_plus_sftloss_step1000tmp07text1K<n<10K0 likes6 downloads2y agoHugging Face 07mlfoundations-dev /ot3_300k_more_ckpts_step1000_eval_27e9 mlfoundations-dev/ot3_300k_more_ckpts_step1000_eval_27e9 Precomputed model outputs for evaluation. Evaluation Results LiveCodeBench Average Accuracy: 34.64% ± 0.87% Number of Runs: 6 Run Accuracy Questions Solved Total Questions 1 33.86% 173 511 2 30.92% 158 511 3 36.79% 188 511 4 35.62% 182 511 5 34.44% 176 511 6 36.20% 185 511 tabular1K<n<10K0 likes6 downloads1y agoHugging Face 08tmpmodelsave /type134_step1000tmp10text1K<n<10K0 likes2 downloads2y agoHugging Face

Listings come live from the Hugging Face Hub API. CoolFace does not host these files.