CoolFace
20 results

dsl

dslighfdsl /humaneval_pythontext10K<n<100K0 likes3.1k downloads2y agoHugging Facedslighfdsl /human_eval_cpptext10K<n<100K1 likes2.3k downloads2y agoHugging Facedslighfdsl /dust3r_newimage10K<n<100K0 likes2.3k downloads2y agoHugging Facedslighfdsl /BigCodeBench_1text1M<n<10M0 likes1.8k downloads2y agoHugging FaceDSLO /DSLO_v0.6_Semantic_Substrate_Specification.pdfDSLO v0.7 → v0.8 Continuity Metadata Block Release Alignment: MODE_A_PUBLIC_SAFE Substrate Depth: SURFACE_ONLY Scientific Orientation Point DSLO v0.8 Scientific Overview DOI: 10.5281/zenodo.22181245 Orientation Class: Overview_DSLO (Root Manifold) Continuity Rule: v0.7 → v0.8 (Registry v0.8 DOI) Core v0.8 Scientific Surfaces Geometry v0.8 — 10.5281/zenodo.21970123 Domain v0.8 — 10.5281/zenodo.22179299 Formatting v0.8 — 10.5281/zenodo.22179509 Registry v0.8 — 10.5281/zenodo.22181076 Machine… See the full description on the dataset page: https://huggingface.co/datasets/DSLO/DSLO_v0.6_Semantic_Substrate_Specification.pdf.0 likes1.6k downloads18d agoHugging FacedSLLab /CausalBench CausalBench Causal graphs of LLM-agent action trajectories for detecting multi-step prompt-injection attacks. Each row is one trajectory represented as a causal graph (nodes = agent actions, edges = causal dependencies) labelled as attack or benign. Part of CausalTrace: https://github.com/decentralizedsciencelab/CausalTrace Contents Config Split Rows Description attack train 17,976 Trajectories containing an injected attack (is_attack = true) benign… See the full description on the dataset page: https://huggingface.co/datasets/dSLLab/CausalBench.tabulargraph-ml10K<n<100K0 likes1.5k downloads3mo agoHugging Face