Publish experimental Decision 3.0 Core AI conversion with reproducible validation

ffa8431 verified 1 day ago

6.02 kB

license: apache-2.0
base_model: vllm-sr/d3-edge
pipeline_tag: zero-shot-classification
tags:
  - coreai
  - apple
  - decision-model
  - multimodal
  - experimental
  - vision
  - video

d3-edge — experimental Apple Core AI conversion

Community conversion of vllm-sr/d3-edge at revision 18d61df78684675463af9ae732872478845c5a79. Converted by Max Farrell. This is an Apple Core AI .aimodel bundle for macOS 27, with its text backbone, original 255-way answer readout, and vision encoder. Choice, yes/no (noul), and score questions run through Core AI; tokenization, media decoding, and result formatting run on the host. No text is generated.

Experimental, with measured numerical drift. All 10 smoke cases selected the same answer as the official BF16 PyTorch runtime on identical resized inputs. The largest absolute probability difference was 0.053746. These are small conversion smoke tests, not a quality benchmark, calibration result, or evidence of equivalence on arbitrary inputs. Fixed-capacity padding and Core AI's BF16 execution can change probabilities and may change decisions on other inputs. The initial 0.02 probability-parity target was not met by every model; the full values are reported rather than claimed as strict numerical parity.

Capacity and changes from upstream

One question per forward pass; system_one processes several questions sequentially.
512 combined tokens, including visual tokens and all prompt text. Oversized requests raise an error; nothing is truncated.
Images and sampled video frames are resized to 224×224, including aspect-ratio changes. Each image or two-frame video patch group occupies 49 visual tokens. This is much smaller than upstream's default image/video resolution.
Multiple images/videos work only when their complete prompt fits. Video decoding retains upstream's 2-fps sampling, at least 4 and at most 32 frames; long sampled clips may exceed the 512-token limit and are rejected.
Up to 255 answer codes are retained; the prompt capacity generally limits practical option count well before 255.
The original BF16 backbone weights and FP32 decision head are retained. Linear attention stays causal; full attention remains noncausal as upstream specifies.
Default specialization was tested on this Mac. Forced CPU-only specialization crashed inside Apple's compiler during development. No verified Neural Engine/GPU placement, iPhone compatibility, speedup, or power-efficiency claim.

Use

hf download maxffarrell/d3-edge-CoreAI --local-dir d3-edge-CoreAI
cd d3-edge-CoreAI
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

import asyncio
from coreai_d3 import D3CoreAI

async def main():
    model = await D3CoreAI.load(".")
    result = await model.system_one(
        state="The customer was charged twice.",
        questions={"route": {
            "type": "choice",
            "instructions": "Which team should handle this?",
            "criteria": {"billing": "Payments", "shipping": "Delivery"}
        }},
        # images=["receipt.png"],
        # videos=["clip.mp4"],
    )
    print(result)

asyncio.run(main())

All neural inference in this adapter uses decision.aimodel and vision.aimodel. PyTorch/Transformers are dependencies for conversion and host preprocessing; source PyTorch weights are not included or needed for inference. Core AI may write a local specialization cache on first load. The adapter uses the upstream prompt formatter and typed response shapes.

Validation

macOS 27.0.1, coreai-core==1.0.0b3, default specialization. The BF16 reference uses Transformers 5.17.0 and the pinned upstream checkpoint. Images and video are compared using the same 224×224 input pixels, not against upstream's original full-resolution run. Text includes choice, noul, score, Spanish, 10 options, and a 433-token case. Additional checks cover one image, two images, video, and rejecting oversized text. End-to-end system_one is separately smoke-tested without loading source weights.

Case	Tokens	Options	Selected answer matches	Max probability difference
text / choice	95	3	Yes	0.000272
text / noul	97	2	Yes	0.000006
text / score	102	4	Yes	0.003266
text / choice	106	3	Yes	0.001970
text / choice	149	10	Yes	0.000541
text / choice	433	2	Yes	0.000011
image / choice	145	3	Yes	0.003389
image / noul	145	2	Yes	0.015024
images / noul	196	2	Yes	0.002397
video / choice	340	3	Yes	0.053746

See validation.json for per-case records. Its elapsed times include reference work and are not inference benchmarks.

Reproduce

Download the exact source revision, convert, and reassemble into a fresh output directory:

hf download vllm-sr/d3-edge --revision 18d61df78684675463af9ae732872478845c5a79 --local-dir upstream/d3-edge
python convert.py --source upstream/d3-edge --output bundles/d3-edge-CoreAI --length 512 --precision bfloat16
python package.py d3-edge
python validate_mm.py d3-edge

coreai-torch==0.4.3 warns that PyTorch 2.14.0 is newer than its validated range; the supplied environment is the version used for these exports and smoke tests. UPSTREAM_MANIFEST.json describes original source files; SHA256SUMS verifies this converted bundle.

Attribution and license

Original model: vLLM Semantic Router Team, based on the Qwen model identified in UPSTREAM_NOTICE. Original model and this conversion are Apache-2.0; see LICENSE and NOTICE. The prompt contract and host decision formatting/media loader are included from the pinned upstream source. The upstream runtime contains an Apache-2.0 noncausal attention hook adapted from Perplexity AI and retains its original attribution. This is an independent community conversion, not an official Apple or vLLM release.