NandhaKishorM/laya
- Source
- GitHub
- First trending
- Category
- Model inference
- GitHub stars
- 27,712
- Main language
- Python
This page introduces an external open-source repository. It is not an HDATF product.

What it does
A multilingual decision engine that answers typed questions about text, email, tickets, or JSON in a single forward pass. A router selects a checkpoint for each request.
How it helps ATF
Harness can compare its typed-question approach when designing decisions based on task state. ATF Works can reference it for questions about email or ticket content.
License
Apache-2.0 Permissive, with a patent grant. Commercial use is allowed; keep the notices and state your changes.
More in this category
- dexmal/dexbotic
A PyTorch toolbox for vision-language-action research covering pretraining, fine-tuning, inference, and evaluation. It provides multiple model configurations, a unified robot training data format, and deployment scripts. - bespokelabsai/nimble
A typed-decision model project sharing data curation, training, and serving methods. Given text and a question schema, it returns selected choices or true-or-false answers with probabilities for allowed answers. - whitecircle/halo
A training framework for language and multimodal models supporting pretraining, supervised fine-tuning, preference optimization, and asynchronous multi-turn reinforcement learning. It runs Hugging Face models on one GPU or across nodes. - featherless-ai/simple-jev
Uses compatible open models for structured classification and scoring without training a separate classifier head. The server constructs JSON choices, rubric scores, or truth and support judgments from next-token logits rather than generated JSON text. - jaredpalmer/kev
Small Qwen3.5-based decision models with pretrained weights, training code, and evaluation data. The API supports yes/no, multiple-choice, and rating questions and matches TypeSafe System One.
Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.