OPEN
JDI-Decision-V1
JDI-Decision-V1 combines a 27B decision backbone with vision and PaddleOCR. Read what its full-system public score and reported GPU timings measure.
By JD Industrials · Weights upload: 1 Nov 2026
A Qwen3.8-27B decision system that combines vision features with frozen PaddleOCR v5 transcriptions. OCR and image encoding run concurrently on one GPU. Published vision scores and timings cover the whole system; the internal decision backbone alone omits OCR.
Quick answers
What is JDI-Decision-V1 by JD Industrials?
JDI-Decision-V1: A Qwen3.8-27B decision system that combines vision features with frozen PaddleOCR v5 transcriptions.
Who makes JDI-Decision-V1?
JDI-Decision-V1: JD Industrials
Facts
- Base and size
- Qwen3.8-27B with D3 decision adaptations
- Inputs
- Text and images, including internal OCR transcriptions
- Runtime
- Python 3.12 and CUDA; complete-system ComboEngine or custom AutoModel loader
- Licence
- Apache-2.0 model tag; OCR components retain upstream terms
- Access
- Public weight shards, complete-system inference code and reproduction guide
Claims and sources
- The maker reports public Decision Index Vision skill 79.7313 on 12,210 successful requests, with 263.4 ms median on H200 replicas. Loading is excluded. Private evaluation and official RTX PRO 6000 timing validation remain pending; this is not a confirmed full-board rank. vendor reportedsource
Links
Source: Model card and weights →
Related projects
No related projects are listed in the registry.