---
license: apache-2.0
base_model: Mapika/decider-0.8b
language:
- en
pipeline_tag: text-classification
tags:
- executorch
- mlx
- apple-silicon
- fp16
---

# decider-0.8b: compact ExecuTorch MLX export

Converted from [Mapika/decider-0.8b](https://huggingface.co/Mapika/decider-0.8b), checkpoint revision
`1ea54127d3bd52f6d753d9257b32a6380b873907`. Original model, training, typed-decision interface and
calibration: **Mark Marosi / Mapika**, based on Qwen3.5. No additional training
or fine-tuning was performed for this export.

## Execution changes and credits

FP16 weights/activations, FP32 recurrent state, fused projections/normalization,
padding removal, and bounded parallel suffix recurrence. Prefixes may be shared
within a request; no answers or state are cached across requests.

Export source: [Decider MLX fork](https://github.com/edbordin-linktree/decider/tree/2619f961b6f7f57b2a62745666f124ec889f5deb). PyTorch/ExecuTorch, Apple MLX,
Qwen and Hugging Face Transformers supply the underlying implementation and
runtime components. No upstream endorsement is implied. The Apache-2.0 license
is included. These are export/runtime changes, not a newly trained model.

## Download and call

Designed for local inference on Apple Silicon using the ExecuTorch MLX backend.
Install the [MLX runtime and fork](https://github.com/edbordin-linktree/decider/blob/apple-silicon-mlx/docs/mlx.md#install-the-runtime), then:

```python
from decider.mlx_backend import MLXDecider

model = MLXDecider.from_pretrained("edbordin-linktree/decider-0.8b-executorch-mlx")
result = model(
    {"ticket": "I was charged twice. Please refund the duplicate."},
    {"team": {"type": "choice", "instructions": "Which team should handle this?",
              "criteria": {"billing": "Charges, invoices and refunds",
                           "technical": "Bugs and technical problems"}}},
)
print(result["answers"])
```

Or start the compatible local HTTP server:

```sh
python -m decider.serve --backend mlx --model edbordin-linktree/decider-0.8b-executorch-mlx
```

The loader downloads and caches the complete bundle automatically, including
calibration and tokenizer assets. Set `revision="COMMIT_HASH"` in Python or
`--revision COMMIT_HASH` on the server to pin a release. After the first download,
Python's `local_files_only=True` loads the cached bundle offline.
This is an ExecuTorch artifact, not an `mlx-lm` or Transformers checkpoint.

Only load trusted artifacts. Verify files against `SHA256SUMS`. Provenance and
the binary checksum are in `provenance.json`. Tested: Python 3.12, Torch 2.14.0,
ExecuTorch 1.5.0, Transformers 5.17.0, M4 Pro Mac with 48 GB memory. Other runtime
versions/hardware and operation without full Xcode are not yet validated.

## Limits

- Maximum 575 rendered tokens per row, subject to separate prefix
  and suffix bounds of 512 and 63 tokens.
- Up to 6 rows per forward; the adapter splits larger groups.
- No larger reference fallback: unsupported shapes fail. No vision or 32k
  context support in this compact artifact.
- Inherits the base model's limitations, including imperfect conditional-rule
  following. Small numerical parity checks are not a general accuracy benchmark.
- Run one model at a time. Export/parity tests use much more memory than serving.
  A 48 GB test machine does not establish compatibility with every smaller Mac.

See the upstream model card for training details and evaluations; those results
belong to the model authors, not this conversion.