convaiinnovations/laya-multilingual

text-classification model by convaiinnovations

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Non-autoregressive System 1 decision model covering 100+ languages. Give it a state (text, email, ticket, or JSON) and typed questions; it returns typed answers with probabilities in a single forward pass. No text generation, so nothing to parse and nothing to hallucinate. Part of the Laya family — use this checkpoint for anything that is not English. Routing is per request, so a mixed workload otherwise pays a checkpoint swap on every language change. Load the ones you expect once, up front, and every later call is just a forward pass: router.attach("multilingual", agent) registers an Agent you already built, so a process that loaded this checkpoint directly can hand it to the router instead of loading it twice. Routing is decided from the script of the input, before the forward pass — because the model's confidence gives no warning when a checkpoint cannot read its input (see below). Measured across…

convaiinnovations/laya-multilingual on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-09-21T09:36:42.973Z

Inside the original model card — Document outline
  1. Laya Multilingual
  2. Quickstart
  3. Let the Router choose
  4. Why this checkpoint exists
  5. XNLI (15 languages)
  6. Speed — it is also the faster checkpoint
  7. Architecture
  8. Limits
  9. Links

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

convaiinnovations/laya-multilingual is a text-classification model repository published by convaiinnovations on Hugging Face. The source reports the transformers 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
transformers
Recent downloads (30 days)
0
Cumulative likes
87
Hugging Face trending score
85
Reported safetensors parameters
321,908,998
Architecture
Not reported
License
apache-2.0
Access
Not gated by Hugging Face
Created
2026-09-19T03:23:34.000Z
Last modified
2026-09-19T09:55:03.000Z

Compatibility and lineage

Reported languages: multilingual, en, de, fr, es, pt, it, nl, sv, da, nb, ru, pl, tr, ar, he, fa, ur, hi, bn, ta, te, kn, ml, th, vi, id, ms, tl, ja, ko, zh, el, hu, fi, ro, sq, sl, sw, af

Base-model lineage was not included.

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.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-09-21T06:36:47.722Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models

BAAI/bge-reranker-v2-m3

ProsusAI/finbert

meta-llama/Prompt-Guard-86M

Mapika/decider-2b

bespokelabs/Bespoke-Nimble-9B

AlexWortega/openjev