jeb for Ollaya

Ollaya package of frontier-infra/jebadiah-4b-v2-GGUF and frontier-infra/jebadiah-9b-v2-GGUF and frontier-infra/jebadiah-27b-GGUF by Jason Brashear, AINode (frontier-infra). Ollaya runs open decision models locally, the way Ollama runs LLMs: typed questions in, calibrated answers out, behind a TypeSafe-compatible API.

ollaya run jeb

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 authors' own weight files by byte offset, so ollaya pull downloads the weights from the upstream repositories, unmodified and pinned to a commit, and verifies their sha256.

Tag	Upstream	Files
jeb:4b	frontier-infra/jebadiah-4b-v2-GGUF@7f671f9	4b/decision.json, 4b/calibration.json
jeb:9b	frontier-infra/jebadiah-9b-v2-GGUF@adaec6b	9b/decision.json, 9b/calibration.json
jeb:27b	frontier-infra/jebadiah-27b-GGUF@7451e61	27b/decision.json, 27b/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 runner matches stock llama-server of the pinned build (b11146) on the same GGUF, CUDA (RTX 4090): 494 questions per model, every decision the same, option logits within 7.7e-6 and probabilities within 2.4e-6. The prompts are identical to the authors' jebadiah_prompt.Renderer on 1,349 test prompts.

License

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