Instructions to use convaiinnovations/laya with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use convaiinnovations/laya with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="convaiinnovations/laya")# pip install -U transformers accelerate # Load model directly from transformers import LayaTypedDecisions model = LayaTypedDecisions.from_pretrained("convaiinnovations/laya", device_map="auto") - Laya
How to use convaiinnovations/laya with Laya:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Inference
- Notebooks
- Google Colab
- Kaggle
Free hosted endpoint for Laya, Jev-compatible API
I was curious how well Laya works and put up an endpoint to curl against it using the same format
as Cloudflare's Jev API. Free, no key:
curl https://laya.inference.zaitlabs.com/ai/run \
-H "Content-Type: application/json" \
-d '{
"state": "Help! My payouts have been failing for 3 days.",
"questions": {
"is_urgent": {"type": "noul", "instructions": "Does this convey urgency?"}
}
}'
{"answers":{"is_urgent":{"type":"noul","noul":0.7894}}}
All three checkpoints from this repo are loaded; by default it picks one by the language of the
state, laya/english, laya/multilingual or laya/typed-decisions forces one. There is also an
OpenAI-style /v1/chat/completions where the fields of the response_format schema are the
questions, so the OpenAI SDKs work unchanged. Weights are pinned to this repo's revision of
18 September 2026.
Requests and responses may be stored and used to tLink header on
every response say so), so don't send anything sensitive. Hosted in the EU, rate-limited per IP,
docs at https://laya.inference.zaitlabs.com/docs
Not affiliated with Convai Innovations.