---
license: apache-2.0
base_model: JohnP1/d1a-e4b-it
base_model_relation: quantized
library_name: mlx
pipeline_tag: text-classification
language: [en, ja]
tags: [d1a, decision-model, pull-requests, mlx, apple-silicon, quantized, 8-bit, on-device]
---
# D1A-E4B-it v0.6 · MLX 8-bit
This repository mirrors [JohnP1/d1a-e4b-it-mlx-q8](https://huggingface.co/JohnP1/d1a-e4b-it-mlx-q8) `v0.6` byte for byte (the same files, checked by LFS sha256), under tag `v0.6`.
**A small decision model for Apple Silicon: give it a document and a few questions, and it picks the answers.** Each question
is yes/no, multiple choice or a score; D1A returns a calibrated probability for every option in one forward pass, with no
generated text, so every answer is a valid option.
This is the 8-bit MLX build of [JohnP1/d1a-e4b-it](https://huggingface.co/JohnP1/d1a-e4b-it) v0.6, with the adapter merged
into its weights. Scores, training and limits are on that card; how far this build moves from the served chat build is below.
```python
from d1a import D1A # pip install "d1a[serve,mlx,media] @ git+https://github.com/jonpol01/d1a" (needs jonpol01/d1a#261)
m = D1A.load("mlx-community/d1a-e4b-it-8bit@v0.6")
m.decide("The customer was charged twice for the same order and wants a refund today.",
{"team": {"type": "choice", "instructions": "Which team handles this?",
"criteria": {"billing": None, "shipping": None, "support": None}},
"angry": {"type": "noul", "instructions": "Is the customer angry?"}})
```
**Not a chat model.** This build has the adapter merged into its weights, so it answers D1A decisions only; text generated
from it would come from a changed backbone, not Gemma 4 E4B-it. To chat with the same model that decides, build an unmerged
folder from the adapter: see [Enable chat](https://huggingface.co/JohnP1/d1a-e4b-it#enable-chat).
**``: encode with it.** The Gemma 4 E4B-it tokenizer adds no ``, but this model was trained with one at the start
of every record (`d1a_config.json` records `leading_ids: [2]`). If you encode requests yourself, prepend id 2.
## What's inside
- the LoRA adapter merged into Gemma 4 E4B-it (revision `ee0ef602`); linear layers and token embeddings 8-bit (group 64), per-layer embeddings 4-bit;
- pointer head fp32 (`head.safetensors`);
- calibration temperature 1.55 in `d1a_config.json`, the run's, not refitted for this build; no use-case temperatures;
- 6.1 GB on disk for the text model, plus 0.9 GB of photo, voice and video encoders in `media/` (unchanged from the -it base).
## Against the served build
Same code, this build against the unmerged 8-bit chat build the Mac mini serves (`quality_gate.py`, Apple M1 Max): 145 demo requests (202 questions) and 92 PR-labeler states (276 questions).
- **1 of 202** demo answers and **3 of 276** labeler answers change; largest probability change 0.073;
- model time 1.01× the chat build's.
Numbers on the [D1A-E4B-it card](https://huggingface.co/JohnP1/d1a-e4b-it) were measured on the chat build, so they carry over to this build within those flips.
## Run it
```bash
pip install "d1a[serve,mlx,media] @ git+https://github.com/jonpol01/d1a"
python -m d1a.serving.serve --run mlx-community/d1a-e4b-it-8bit@v0.6 --port 8009
```
## Limits
- Everything on the [D1A-E4B-it card](https://huggingface.co/JohnP1/d1a-e4b-it#limits) applies.
- **The adapter is merged**, so this build cannot chat (above).
- **``**: requests encoded without the leading id 2 are out of distribution.
## Versions
| Tag | What it is |
|---|---|
| **`v0.6`** | **MLX 8-bit build of D1A-E4B-it v0.6 (adapter merged)** |
## License and data
Apache-2.0. Base model: Gemma 4 by Google (Apache-2.0). Code: [github.com/jonpol01/d1a](https://github.com/jonpol01/d1a), built on Kev by Jared Palmer (Apache-2.0). Japanese decision data derived from JGLUE by Yahoo Japan Corporation and Waseda University (CC BY-SA 4.0). Pull-request data from NousResearch/hermes-agent (MIT); the labelled PR dataset itself, including the recent PRs, is private.