5 shown

datasets

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

01Helmo21 /asia-fertility asia-fertility — results Tokenizer cost ratios, multi-turn NIAH recall, and wall-clock latency measurements for 16 lower-resource Asian languages × 10 frontier tokenizers, with bootstrap 95% confidence intervals. 📄 Preprint (Zenodo): 10.5281/zenodo.21069313 💻 Code: Helmo21/asia-fertility 🌐 Web app: fertiscope.vercel.app Generated by asia-fertility v0.4.0. Configs (use with datasets) from datasets import load_dataset # Benchmark A — main leaderboard (160 rows:… See the full description on the dataset page: https://huggingface.co/datasets/Helmo21/asia-fertility.tabular1K<n<10K0 likes38 downloads3mo agoHugging Face 021-800-LLMs /narrative_qa_helmtext1K<n<10K0 likes13 downloads1y agoHugging Face 031-800-LLMs /quac_helmtext10K<n<100K0 likes4 downloads1y agoHugging Face 041-800-LLMs /truthfulqa_helmtextn<1K0 likes2 downloads1y agoHugging Face 05alistaireid /helmtabularn<1K0 likes1 downloads2y agoHugging Face

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