A Myanmar-language Laya checkpoint trained on Davlan/sib200, with a Gradio demo space from the same author.
GitHubMultilingual
Multilingual
10 builds
An Arabic Laya checkpoint trained on AmazonScience/massive and facebook/xnli, with a companion laya-ara-rag ranking model from the same author.
GitHubMultilingual
laya-ara: Laya fine-tuned for Arabic NLU on MASSIVE and XNLI
Google's LiteRT community conversion of the multilingual checkpoint (tflite), tagged for Android text classification. An English LiteRT build is published alongside it.
GitHubMultilingual
Laya multilingual in LiteRT for Android and on-device
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.
GitHubMultilingual
Feishu message classification bench: Jev 64/64, Laya 20/64 on 64 frozen scenarios
- Single choice
- Jev 64/64, Laya 20/64
20 real-world Chinese requests × 3 checkpoints, measuring accuracy, latency and whether confidence knows when it is wrong. Includes a Windows/Python 3.14 segfault workaround.
Automotive, embedded, enterprise software and product decisions, three trials each, with questions, expected answers, raw responses and a static HTML report.
GitHubMultilingual
Japanese business-judgment benchmark: Jev 97.6 vs Laya 36.9 on the same 40 questions
- Jev 1.13.0
- 97.6 / 100
- Laya multilingual FP16
- 36.9 / 100
Reproducible zero-shot benchmark on informal Moroccan Darija reviews in Arabic script and Arabizi, positive/neutral/negative. Deterministic seed-42 split, no training.
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.
Tested Jev vs Laya (local, MLX) on 40 support tickets, EN + Thai. Jev 90–100%. Laya zero-shot 30–80%. Laya's faster, but not close on accuracy yet.
X postMultilingual
40 support tickets in English and Thai: Jev 90–100%, Laya zero-shot 30–80%
- Jev
- 90–100%
- Laya zero-shot
- 30–80%
GGUF conversions of both the English and multilingual Laya checkpoints for llama.cpp-style local runtimes.
GitHubMultilingual