madewithlaya

Catalog / Multilingual

0105GitHub

Does a typed-judgment model rerank Finnish legal passages better than a cross-encoder?

Postgres FTS, pgvector and RRF first stage; Jev, Voyage, GPT-4.1-mini, GPT-5.6-luna and open-weight Laya as rerankers on two Finnish legal corpora. Recall, MRR, nDCG, latency.

Open source ↗ github.comcost$/1000 queries reported per rerankertime-
laguagu/jev-rerank-benchREADME ↗

README not available at build time.

Also filed under Multilingual

  1. 0115

    Laya fine-tuned for Burmese topic classification on SIB-200

    A Myanmar-language Laya checkpoint trained on Davlan/sib200, with a Gradio demo space from the same author.

    aungthuhein-dev · Multilingual · free

  2. 0114

    laya-ara: Laya fine-tuned for Arabic NLU on MASSIVE and XNLI

    An Arabic Laya checkpoint trained on AmazonScience/massive and facebook/xnli, with a companion laya-ara-rag ranking model from the same author.

    Wouze · Multilingual · free

  3. 0111

    Laya multilingual in LiteRT for Android and on-device

    Google's LiteRT community conversion of the multilingual checkpoint (tflite), tagged for Android text classification. An English LiteRT build is published alongside it.

    litert-community · Multilingual · free, on-device

  4. 0109

    Feishu message classification bench: Jev 64/64, Laya 20/64 on 64 frozen scenarios

    Synthetic Chinese workplace-chat scenarios with frozen inputs, prompts and labels. Reports classification quality, mis-generated tasks and latency: Jev 253 ms vs Laya 151 ms.

    Feng · Multilingual · 151 ms (Laya) vs 253 ms (Jev)