MNN-Pocket-0.3B-Dec decision model
MNN-Pocket-0.3B-Dec bundles a small text backbone, adapter and decision head. Read its Chinese/English inputs, request limits and calibration fit.
By Taobao MNN · First published Hugging Face package; October catch-up: 15 Oct 2026
A text decision package with the MNN-Pocket-0.3B backbone, an unmerged LoRA adapter and a pointer head. It returns probabilities for supplied choices, yes/no questions and ordered scores. The bundled Transformers/PEFT runtime keeps the full backbone and language-model head.
Quick answers
What is MNN-Pocket-0.3B-Dec by Taobao MNN?
MNN-Pocket-0.3B-Dec: A text decision package with the MNN-Pocket-0.3B backbone, an unmerged LoRA adapter and a pointer head.
Who makes MNN-Pocket-0.3B-Dec?
Facts
- Package
- 723 MB backbone, 28.7 MB adapter and 1.8 MB decision head, per the card
- Inputs
- Chinese and English text; up to 255 candidates per question
- Context
- 32,768 request tokens; longer requests raise an error instead of truncating
- Access
- Bundled Python runtime; CPU float32 or supported GPU dtypes
- Licence
- Apache-2.0 file included
Claims and sources
- The maker fitted a temperature of 1.1112 on a 600-question calibration partition, reducing pooled NLL from 0.8598 to 0.8576. This calibration fit does not establish held-out task accuracy or phone performance. vendor reportedsource
Links
Source: Card and weights → Source: Runtime → Source: Calibration record → Source: Licence →
Related projects
No related projects are listed in the registry.