22nd of 5 in Open models
laya
Single-pass multilingual classifier for typed choice, score and yes/no decisions
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 32.9k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
0 on 16 Sept 202632,915 on 14 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Laya answers typed questions (choice, score, noul) about a text, email, ticket or JSON state in one forward pass of an encoder model, with no text generation. A Router picks between three checkpoints (ModernBERT-large English, mmBERT-base multilingual for 100+ languages, and a typed-decisions fine-tune). It ships as a Python package with a CLI, optional HTTP and MCP servers, and LangChain, LlamaIndex and CrewAI integrations.
Who it is for: Engineers needing fast multilingual triage, routing and moderation classifiers
Strengths
- One forward pass: 33 ms per question, 7.2 ms/question batched, measured on a T4
- No generation, so no output parsing; answers are typed choice, score or probability
- Router selects English or multilingual checkpoint per request; 100+ languages covered
- Fine-tuning notebooks provided; typed-decisions checkpoint scores 0.766 vs 0.362 for base English
Weaknesses
- Zero-shot accuracy is low on domain tasks; fine-tuning is needed for good results
- Multilingual checkpoint ships with a 1,024-token limit; beyond about 4,000 tokens accuracy varies
- Only classifies fixed question types; cannot generate or explain text
- Checkpoints download from Hugging Face on first use, so offline setups need preparation
What it needs
- GPU optional
- Docker + Compose
- Needs Hugging Face Hub (checkpoint download), PyTorch, transformers
- Models: ModernBERT-large (421M), mmBERT-base (322M), ONNX Runtime
Head to head
Also in Open models
See all 5| Rank | Project | Score |
|---|---|---|
| 1 | llmfitRust tool that checks which LLMs fit your RAM, CPU and GPU | 80 out of 100 |
| 3 | timesfmPretrained time-series foundation model for zero-shot forecasting from Google Research | 65 out of 100 |
| #4 | kronosPretrained decoder-only models that forecast financial candlestick (K-line) series | 47 out of 100 |
| #5 | clipOpenAI's reference PyTorch code and weights for contrastive image-text embeddings | 29 out of 100 |