alice-noa-chan/ayaka-large
text-classification model by alice-noa-chan
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.
Ayaka large is an open, MIT-licensed decision model for Jev-style structured decisions. You give it a state and typed questions (noul / choice / score), and it returns a calibrated probability for every candidate label. It is a LoRA adapter plus a small decision head on google/gemma-4-12B-it (text stack only, base revision 707f0a3b8a3c7ad586ed01e27eafbad8a27dd0f7). It is trained only on license-clean data. Code, training pipeline and documentation: A Dockerfile with the exact base image, pinned by digest, is in the repository. Verified environment: (image runpod/pytorch:2.8.0-py3.11-cuda12.8.1-cudnn-devel-ubuntu22.04). tokenizers 0.23.2. torch. This repository holds only the adapter (bf16 safetensors, 525 MB), the head (head.safetensors) and the config. The base model is fetched from Google's repository at the pinned revision. The server speaks TypeSafe's POST /v1/systemone format and returns a probability for every label: usage.inputtokens and usage.outputtokens are reported per request. A question is routed only when all three conditions hold: do not count; A routed…
Read the full model card ↗ · Preview checked 2026-09-28T06:58:01.938Z
Inside the original model card — Document outline
- Ayaka large
- Use (pinned)
- Worked-steps route (--reasoning)
- Results (JevBench public tiers)
- Latency
- Tokens and cost per decision
- Training
- Training data (35 sources)
- Benchmark disclosure
- License
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
alice-noa-chan/ayaka-large is a text-classification model repository published by alice-noa-chan on Hugging Face. The source reports the ayaka 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
- ayaka
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- mit
- Access
- Not gated by Hugging Face
- Created
- 2026-09-28T05:52:34.000Z
- Last modified
- 2026-09-28T05:59:35.000Z
Compatibility and lineage
Reported languages: en, ko, ja
Reported base models: google/gemma-4-12B-it
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 2026-09-28T06:38:00.545Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.