# Laya medical specialty decision model by AI Anytime

> Laya medical specialty classifies clinical notes with Snapcall. Check its open weights, held-out test results, label scope and calibration limits.

Updated 2026-11-12 (Australia/Adelaide)

## Quick answers

### What is Laya medical specialty by AI Anytime?

[Laya medical specialty](<https://decisionmodels.ai/models/laya-medical-specialty>): A [Laya](<https://decisionmodels.ai/models/laya>) fine-tune that assigns clinical notes to a fixed menu of medical-specialty and document-type labels.

[Laya medical specialty facts](<https://decisionmodels.ai/models/laya-medical-specialty>)

[Source](<https://huggingface.co/ai-anytime/laya-medical-decision-model>)

### Who makes Laya medical specialty?

[Laya medical specialty](<https://decisionmodels.ai/models/laya-medical-specialty>): AI Anytime

[Laya medical specialty facts](<https://decisionmodels.ai/models/laya-medical-specialty>)

[Source](<https://huggingface.co/ai-anytime/laya-medical-decision-model>)

By AI Anytime · Hugging Face weight upload, 19:54:59 UTC: 2026-11-11 · OPEN

A [Laya](<https://decisionmodels.ai/models/laya>) fine-tune that assigns clinical notes to a fixed menu of medical-specialty and document-type labels. Snapcall supplies the loader and System One server. Its published test concerns document classification; it does not validate diagnosis or clinical care.

## Facts

- Base: convaiinnovations/laya, fully fine-tuned with Snapcall
- Inputs: AI Anytime reports text-only choice classification over 40 supplied labels
- Access: Public backbone and decision-head safetensors; load or serve with Snapcall
- Training: AI Anytime reports 4,023 training, 447 validation and 496 test examples from galileo-ai/medical\_transcription\_40
- Licence: Apache-2.0 according to the card; dataset terms remain separate

## Claims and sources

- **VENDOR-REPORTED**: AI Anytime reports 64.31% test accuracy, macro-F1 0.5706 and 15-bin ECE 0.0480 on 496 examples. Temperature scaling uses the validation split; calibration must be checked again on new traffic. [source](<https://huggingface.co/ai-anytime/laya-medical-decision-model>)

## Links

- [Source: Card and weights](<https://huggingface.co/ai-anytime/laya-medical-decision-model>)
- [Source: Evaluation record](<https://huggingface.co/ai-anytime/laya-medical-decision-model/blob/main/eval_results.json>)
- [Source: Training and serving toolkit](<https://github.com/AIAnytime/snapcall>)

## Related projects

[Snapcall training and serving](https://decisionmodels.ai/projects#project-snapcall) trains, loads and serves this checkpoint.