newTokenEra decision 27B
newTokenEra decision 27B returns Chinese and English typed answers. It ships BF16 weights and code, with a 4,096-token limit per question.
By NewTokenEra · Hugging Face weight release: 11 Nov 2026
A Chinese/English post-trained Qwen3.8-27B decision model with full BF16 weights. Its decide method scores a 26-slot decision head once per question and returns Choice, Noul or Score answers, without generating text. Its reported N-bank evaluation was also used during interface development.
Quick answers
What is newTokenEra decision 27B by NewTokenEra?
newTokenEra decision 27B: A Chinese/English post-trained Qwen3.8-27B decision model with full BF16 weights.
Who makes newTokenEra decision 27B?
Facts
- Base
- Qwen/Qwen3.8-27B; upstream revision recorded in provenance.json
- Inputs
- Text or JSON state; 1 to 64 questions; Choice has 2 to 26 options and Score has 2 to 10 ordered levels
- Context
- 4,096 tokens per rendered question; longer inputs raise an error rather than truncate
- Access
- 18 BF16 weight shards, about 52.17 GB before runtime overhead; custom Transformers code with trust_remote_code
- Calibration
- Probabilities are conditional on supplied alternatives; downstream-domain calibration is unmeasured
- Licence
- Apache-2.0; actual LICENSE included
Claims and sources
- The maker reports 1,311/1,340 classification and Boolean decisions correct on the development N bank. Its 120 tied mixed decisions are excluded from accuracy; the 300 rating prompts use a separate MAE metric. This is a same-bank regression check. vendor reportedsource
Links
Source: Card and weights → Source: Licence → Source: Provenance → Source: Evaluation record → Source: Typed inference implementation →
Related projects
No related projects are listed in the registry.