| --- |
| license: apache-2.0 |
| base_model: |
| - frontier-infra/jebadiah-4b-v2-GGUF |
| - frontier-infra/jebadiah-9b-v2-GGUF |
| - frontier-infra/jebadiah-27b-GGUF |
| tags: |
| - ollaya |
| - gguf |
| - llama.cpp |
| - decision-model |
| - system-one |
| pipeline_tag: text-classification |
| --- |
| |
| # jeb for Ollaya |
|
|
| [Ollaya](https://github.com/ollaya-dev/ollaya) package of **[frontier-infra/jebadiah-4b-v2-GGUF](https://huggingface.co/frontier-infra/jebadiah-4b-v2-GGUF)** and **[frontier-infra/jebadiah-9b-v2-GGUF](https://huggingface.co/frontier-infra/jebadiah-9b-v2-GGUF)** and **[frontier-infra/jebadiah-27b-GGUF](https://huggingface.co/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. |
|
|
| ```sh |
| ollaya run jeb |
| ``` |
|
|
| ## What is in this repository |
|
|
| This repository holds only the files Ollaya derives, with no weights. The model is the authors' own GGUF |
| file: `ollaya pull` downloads it from their repository, unmodified and pinned to a commit, verifies its |
| sha256, and Ollaya runs it on llama.cpp. |
|
|
| | Tag | The authors' GGUF | Files | |
| |---|---|---| |
| | `jeb:4b` | [frontier-infra/jebadiah-4b-v2-GGUF@7f671f9](https://huggingface.co/frontier-infra/jebadiah-4b-v2-GGUF/tree/7f671f9a31827257c26401000484e154b39417e6) `jebadiah-4b-v2-Q8_0.gguf` | `4b/decision.json`, `4b/calibration.json` | |
| | `jeb:9b` | [frontier-infra/jebadiah-9b-v2-GGUF@adaec6b](https://huggingface.co/frontier-infra/jebadiah-9b-v2-GGUF/tree/adaec6b3d1f0421706deb49fa275ab49093982ff) `jebadiah-9b-v2-Q8_0.gguf` | `9b/decision.json`, `9b/calibration.json` | |
| | `jeb:27b` | [frontier-infra/jebadiah-27b-GGUF@7451e61](https://huggingface.co/frontier-infra/jebadiah-27b-GGUF/tree/7451e611a20ce3f56dd7d87f78c8a25b736c08f5) `jebadiah-27b-Q4_K_M.gguf` | `27b/decision.json`, `27b/calibration.json` | |
|
|
| Each tag has `decision.json` (the prompt, the option labels Ollaya reads and llama.cpp's settings) 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. |
| |
