--- title: jebadiah-4b-v2-MLX canonical_url: "https://www.modelscope.ai/models/JasonBrashear/jebadiah-4b-v2-MLX" md_url: "https://www.modelscope.ai/models/JasonBrashear/jebadiah-4b-v2-MLX.md" repository: JasonBrashear/jebadiah-4b-v2-MLX last_updated: 2026-09-29 license: apache-2.0 pipeline_tag: text-classification tasks: - text-classification base_model: - JasonBrashear/jebadiah-4b-v2 base_model_relation: quantized parameters: 1.8B tensor_type: - U32 - BF16 - F32 library_name: - mlx - safetensors language: - en downloads: 4 stars: 0 tags: - mlx - decision-model - system-one - typed-decisions - calibrated-probabilities - ainode --- # jebadiah-4b-v2-MLX > jebadiah-4b-v2-MLX - An open-source model by JasonBrashear on ModelScope. Mirror of huggingface.co/frontier-infra/jebadiah-4b-v2-MLX. The Hugging Face repo is the source of truth: https://huggingface.co/frontier-infra/jebadiah-4b-v2-MLX. Code and the… JasonBrashear/jebadiah-4b-v2-MLX is a 1.8B-parameter text-classification model on ModelScope. licensed under apache-2.0. derived from JasonBrashear/jebadiah-4b-v2. - **Repository**: JasonBrashear/jebadiah-4b-v2-MLX - **License**: apache-2.0 - **Tasks**: text-classification - **Parameters**: 1.8B - **Base model**: JasonBrashear/jebadiah-4b-v2 - **Tags**: mlx, decision-model, system-one, typed-decisions, calibrated-probabilities, ainode - **Downloads**: 4 - **Stars**: 0 - **Last updated**: 2026-09-29 Source: https://www.modelscope.ai/models/JasonBrashear/jebadiah-4b-v2-MLX --- # Jebadiah 4B v2 MLX > Mirror of huggingface.co/frontier-infra/jebadiah-4b-v2-MLX. The Hugging Face repo is the source of truth: [https://huggingface.co/frontier-infra/jebadiah-4b-v2-MLX](https://huggingface.co/frontier-infra/jebadiah-4b-v2-MLX). Code and the standalone server: [github.com/getainode/jebadiah](https://github.com/getainode/jebadiah). MLX builds of [Jebadiah 4B v2](https://huggingface.co/frontier-infra/jebadiah-4b-v2) for Apple silicon, one folder per precision (`8bit/`, `4bit/`, group size 64). Jebadiah answers a typed question (choice, noul or score) with a probability for every option, read from one forward pass. Nothing is generated. Code, trainer and evals: [getainode/jebadiah](https://github.com/getainode/jebadiah). **Results and docs** - Project site, with every result and how to run the models: [jebadiah.ai](https://jebadiah.ai). - For the family: [Decision Index 0.2.1](https://huggingface.co/spaces/multimodalart/jev-decision-index): the 27B scores 54.67, #5 of 67 open models (as of 2026-09-26). This is the board's own number; the maintainer validated my run and put it on the leaderboard. [Run record](https://huggingface.co/datasets/frontier-infra/jebadiah-decision-index-results/tree/main/runs/jebadiah-27b-1c0d794f). - JevBench v1.4.2: on its 231 public items, run through its own harness, Jebadiah 27B scores 0.866, the same as Jev 1.13.0; Jebadiah 9B v2 scores 0.818. This is my own run on the public items, not the official board, which also uses sealed items. [Details and caveats](https://github.com/getainode/jebadiah#where-we-stand-on-jevbench). The 4B has not been run on either. - All sizes: the [Hugging Face collection](https://huggingface.co/collections/frontier-infra/jebadiah-open-system-one-decision-models-6ab80765ddd3fa0b3eba5213), mirrored on [ModelScope](https://www.modelscope.ai/profile/JasonBrashear). **Which one should I use?** For local use, start with [Jebadiah 9B v2 GGUF](https://huggingface.co/frontier-infra/jebadiah-9b-v2-GGUF). On Apple silicon, use an MLX build: [27B](https://huggingface.co/frontier-infra/jebadiah-27b-MLX), [9B v2](https://huggingface.co/frontier-infra/jebadiah-9b-v2-MLX) or [4B v2](https://huggingface.co/frontier-infra/jebadiah-4b-v2-MLX). For vLLM or fine-tuning, use the full weights: [27B](https://huggingface.co/frontier-infra/jebadiah-27b), [9B v2](https://huggingface.co/frontier-infra/jebadiah-9b-v2) or [4B v2](https://huggingface.co/frontier-infra/jebadiah-4b-v2). Setup for every runtime, and for JDE: [Run Jeb locally](https://github.com/getainode/jebadiah/blob/main/docs/run-locally.md). ## Files Every file was checked on the 260 held-out questions the merged weights were checked on, and compared with the merged bf16 weights and with the training run's own eval records. | File | Size | Same answer as bf16 | Same as the run | choice + noul | score | Prob. diff median / max | |---|---:|---:|---:|---:|---:|---:| | `8bit/` | 4.5 GB | **252 / 260** | 253 / 260 | 169 / 173 | 84 / 87 | 0.004 / 0.110 | | `4bit/` | 2.4 GB | **215 / 260** | 215 / 260 | 157 / 173 | 58 / 87 | 0.056 / 0.380 | | *bf16 weights* | | | 259 / 260 | 172 / 173 | 87 / 87 | 0.002 / 0.019 | Which one: `8bit` if your Mac has the memory; `4bit` when it does not. A folder needs about its own size in unified memory, plus about 1 GB for a 2k-token prompt. **`8bit` changes 8 of 260 answers** against bf16 (3 on score questions) and moves probabilities more (median 0.004, max 0.11). Use it only when a larger build does not fit. **`4bit` changes 45 of 260 answers** against bf16 (29 on score questions) and moves probabilities more (median 0.056, max 0.38). Use it only when a larger build does not fit. ## Run it The script renders the prompt exactly as AINode does, runs one forward pass with mlx-lm, multiplies the last hidden state by the option labels' output-head rows in fp32 and applies `temperatures.json` (choice 1.1167, noul 1.3319, score 0.8312). Needs mlx-lm 0.31 or newer (qwen3_5 support). ```bash pip install "mlx-lm>=0.31" hf download frontier-infra/jebadiah-4b-v2-MLX --include "8bit/*" --include "scripts/*" --include temperatures.json --local-dir jebadiah-4b-v2-MLX cd jebadiah-4b-v2-MLX python scripts/decide_mlx.py --model 8bit --request scripts/example-request.json ``` `--no-temperatures` returns the raw probabilities. **HelpSteer2-like traffic.** A held-out HelpSteer2 check (2026-09-29): on the 418 `nvidia/HelpSteer2` validation rows that no reported evaluation set uses (natural label mix, never in the training pool), this model's score answers want a temperature of 1.26, not 0.83, and still 1.08 after reweighting to a flat label mix. If your traffic looks like HelpSteer2, keep the older score temperature, 1.20 (the `train` fit in `temperatures.json`; every script here takes `--temperatures` with a file of your own), or refit on your own labels. v3's calibration split will draw HelpSteer2 from held-out data. On `example-request.json` (8bit/): ```json { "route": {"type": "choice", "choice": "billing", "confidence": 0.394292, "probabilities": {"billing": 0.596195, "support": 0.0839, "sales": 0.319905}}, "urgent": {"type": "noul", "noul": 0.147991} } ``` ## How it was measured Jevals PubMedQA, Banking77 (77 options) and HelpSteer2, plus Nimble: the merge check's fixed sample (seed 20260925), the run's option order and the run's temperatures, so the probability differences compare like with like (the shipped temperatures.json since 2026-09-29 uses 0.8312 for score; top picks do not depend on it). "Same answer" is the top option; "prob. diff" is the largest change on any option against the run's CUDA record. Records: `eval/agreement-*.json`. ## License Apache-2.0, as the base model. Made in Texas.