aac6fef/laya-mlx
text-classification model by aac6fef
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.
Native MLX FP16 conversion of convaiinnovations/laya for Apple silicon. This checkpoint uses ModernBERT-large, a 512-token total context, and Laya's decision Transformer, scoring head and action head. It supports choice, ordinal score, and boolean noul questions. All model computation runs in MLX; the runtime does not require PyTorch or Transformers. Install the dedicated runtime on an Apple silicon Mac with macOS 14+ and Python 3.11+: Use dtype="float32" for closer agreement with upstream FP32 arithmetic. The source weights themselves are FP16. Question formatting, tokenizer behavior, calibration temperatures and output schema are preserved. This is a bidirectional decision encoder loaded with layamlx. The package provides the custom architecture needed to interpret the checkpoint. The repository does not include a generative language model or training implementation. Tested locally…
Read the full model card ↗ · Preview checked 2026-09-23T09:32:24.325Z
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: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
aac6fef/laya-mlx is a text-classification model repository published by aac6fef on Hugging Face. The source reports the mlx 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
- mlx
- Recent downloads (30 days)
- 0
- Cumulative likes
- 68
- Hugging Face trending score
- 65
- Reported safetensors parameters
- 421,293,830
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-19T14:11:30.000Z
- Last modified
- 2026-09-19T16:38:19.000Z
Compatibility and lineage
Reported languages: en
Reported base models: convaiinnovations/laya
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 2026-09-23T06:37:23.610Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.