Model

SZLHOLDINGS on Hugging Face

@stephenlutar2-hashby Stephen Lutar · SZL Holdings

0

48 models, 37 datasets, 38 Spaces and 14 kernels, all public. Each model is labeled by evidence class instead of being presented as a finished model. 18 hold trained weights: small fine-tunes and LoRA adapters on Qwen2.5 and Qwen3.5 bases from 0.5B to 1.5B. Of the rest, 16 are kernel software, 7 are code or scripts, 5 are nano synthetic, and 2 are empty roadmap cards (a11oy.net record, 2026-10-13). None is claimed to be operational or fully benchmarked.

Built withHugging Face HubPEFTllama.cppGradioDockermodelsdatasetslorakernelsprovenance

See what other members are building and what each project is looking for.