Mazino0/kleos-decider-nano
text-classification model by Mazino0
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
A 150M decision model for agent memory. It is a fine-tune of tasksource/tasksource-decider-nano on memory-shaped pair judgements: It is the built-in decider of the kleos database, where it backs decide(), the ::decider commands and the supersession pipeline. The weights version is nano-tune-v1 (kleosdecider.json). kleos ships calibrated thresholds for this version. All numbers come from kleos's Rust inference (decideeval). Thresholds and bias were fitted on 60 adapt items only. The eval sets were never seen in training, and 238 near-duplicates of them were removed from the training data. AUROC is reported with 95% bootstrap CIs. Precision and memory (Apple M-series; kleos-infer, candle): q8 vs f32: 1–2 of 922 decisions flip. kleos uses this model by default: Use the bundled decider.py, which is unchanged from the base model: The model was trained in the…
Read the full model card ↗ · Preview checked 2026-10-27T20:47:46.816Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: mit. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
Mazino0/kleos-decider-nano is a text-classification model repository published by Mazino0 on Hugging Face. The source reports the kleos library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-classification
- Library
- kleos
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 149,015,041
- Architecture
- ModernBertModel
- License
- mit
- Access
- Not gated by Hugging Face
- Created
- 2026-10-23T06:40:46.000Z
- Last modified
- 2026-10-23T06:45:11.000Z
Compatibility and lineage
Reported languages: en
Reported base models: tasksource/tasksource-decider-nano
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-23T06:46:00.441Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.