| --- |
| license: apache-2.0 |
| base_model: |
| - alibiserikbay/JevK5-GGUF |
| tags: |
| - ollaya |
| - gguf |
| - llama.cpp |
| - decision-model |
| - system-one |
| pipeline_tag: text-classification |
| --- |
| |
| # jevk5 for Ollaya |
|
|
| [Ollaya](https://github.com/ollaya-dev/ollaya) package of **[alibiserikbay/JevK5-GGUF](https://huggingface.co/alibiserikbay/JevK5-GGUF)** by alibiserikbay. |
| 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 jevk5 |
| ``` |
|
|
| ## 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 | |
| |---|---|---| |
| | `jevk5:4b` | [alibiserikbay/JevK5-GGUF@ec67b0b](https://huggingface.co/alibiserikbay/JevK5-GGUF/tree/ec67b0bfce5119a8b11a2cdb430bb43e3fa3e82a) `jevk5-4b-v0.3-Q8_0.gguf` | `4b/decision.json`, `4b/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): 593 questions, every decision the same, option logits within 7.7e-6 and probabilities within 1.6e-6. The prompts are byte-identical to the author's jevk5.prompt. |
|
|
| ## License |
|
|
| Same as the upstream model (Apache-2.0). Ollaya itself is Apache-2.0. |
|
|
