gliclass for Ollaya

Ollaya package of knowledgator/gliclass-instruct-large-v1.0 by Knowledgator. Ollaya runs open decision models locally, the way Ollama runs LLMs: typed questions in, calibrated answers out, behind a TypeSafe-compatible API.

ollaya run gliclass

What is in this repository

This repository holds only the files Ollaya derives, with no weights. Each graph is an ONNX export of the original model whose weights reference the author's own model.safetensors by byte offset, so ollaya pull downloads the weights from the upstream repository, unmodified and pinned to a commit, and verifies their sha256.

Tag	Upstream	Files
gliclass:large	knowledgator/gliclass-instruct-large-v1.0@825e547	large/model-fp32.onnx, large/decision.json, large/calibration.json

Each tag has an fp32 graph, used on CPU and GPU. Each tag also has decision.json (sequence layout, special tokens) and calibration.json (temperatures).

Parity

Ollaya's Rust runtime matches the Python reference exactly on 482 questions. The token ids and label positions are identical, and so is the decision on every question. Probabilities are within 1e-5, on CPU and CUDA.

License

Same as the upstream model (Apache-2.0). Ollaya itself is Apache-2.0.