This dataset stores LoRA expert pools and gating network weights from multi-task fine-tuning experiments on various base models (Phi-2, Gemma-2, Llama-3.2, Pythia-410M, Qwen2.5-0.5B, SmolLM-360M). - legacy/{model}/{runname}/ — runs from the original experimental campaign (2024-12 → 2025-01), with checkpoints at steps 500, 1000,..., finalmodel and bestmodel. - New baseline + Gated runs (2026-05+) are uploaded at the top level following the paper-001 pipeline convention. WIP — Master's thesis research artifacts.
Independent publisher
Helain ZIMMERMANN
Helain
NLP, Vision
Models in Library0
Datasets in Library2
Models on Hugging Face2
Followers—
Compare the published evidence
This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.