# decider-ja 0.5B by ken11 > Decider-ja 0.5B returns typed judgments on Japanese text. Read its MIT adapter, GGUF route, uncalibrated probabilities and Lambda timing scope. Updated 2026-11-12 (Australia/Adelaide) ## Quick answers ### What is decider-ja 0.5B by ken11? [decider-ja 0.5B](): A Japanese decision adapter and pointer head trained on Sarashina2.2-0.5B with the [Strands Decider]() recipe. [decider-ja 0.5B facts]() [Source]() ### Who makes decider-ja 0.5B? [decider-ja 0.5B](): ken11 [decider-ja 0.5B facts]() [Source]() By ken11 · Hugging Face weight release: 2026-11-10 · OPEN A Japanese decision adapter and pointer head trained on Sarashina2.2-0.5B with the [Strands Decider]() recipe. It returns Choice, Noul and Score answers through strands-decider. This is a community release, with a separate base download or a merged Q8\_0 GGUF. ## Facts - Base: sbintuitions/sarashina2.2-0.5b - Inputs: Japanese text; training and request configuration use a 4,096-token maximum - Calibration: Temperature 1.0, without calibration; the card warns about long documents, arithmetic, neutral labels and surface-word effects - Training: 200,156 rows for one epoch; translated public data and synthetic data. The mixed training rows and teacher distributions are not published - Licence: MIT; LICENSE.md includes the base and Strands code attribution ## Claims and sources - **VENDOR-REPORTED**: The maker reports median inference 0.94 s for 224 tokens and three questions on AWS Lambda arm64 with 10,240 MB memory, six Graviton2 vCPUs and Q8\_0 GGUF. A separate roughly 220-token one-question test reports median 0.38 s and p95 0.58 s. [source]() ## Links - [Source: Card and packages]() - [Source: Training configuration]() - [Source: Request configuration]() - [Source: Licence]() ## Related projects No related projects are listed in the registry.