modernbert repositories

Trending repositories tagged modernbert, ranked by trending score. Updated daily.

  1. 1
    NandhaKishorM/laya

    Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

    GitHub · Python · 35,756 stars · 3,205 forks · +81 stars in 24 hours · Trending score 3.68

  2. 2
    mizorewww/laya-mlx

    Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

    GitHub · Python · 7,115 stars · 577 forks · +3 stars in 24 hours · Trending score 1.42

  3. 3
    mizorewww/laya-coreml

    Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.

    GitHub · Python · 1,647 stars · 140 forks · +3 stars in 24 hours · Trending score 1.21

  4. 4
    KRLabsOrg/verbatim-rag

    Provenance-first extractive RAG: return verbatim source spans with citations using local ModernBERT or optional LLM-assisted extraction.

    GitHub · Python · 208 stars · 40 forks · 0 stars in 24 hours · Trending score 0.03

  5. 5
    Leb947/modernbert-multi-task-studio

    ModernBERT Multi-Task Fine-Tuning Hub 2026: Streamlined AI Workflows

    GitHub · HTML · 57 stars · 0 forks · 0 stars in 24 hours · Trending score 0.02

  6. 6
    jlt-commons/lev

    Jolt implementation of Laya non-autoregressive System 1 decision engine

    GitHub · Clojure · 30 stars · 1 forks · 0 stars in 24 hours · Trending score 0.02

  7. 7
    petkyletampu28-a11y/tasknet-multitask

    Modern Multi-Task NLP Fine-Tuning Framework with ModernBERT 2026

    GitHub · HTML · 53 stars · 0 forks · 0 stars in 24 hours · Trending score 0.02

  8. 8
    Heman10x-NGU/Verdict-open-jev

    Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground

    GitHub · Python · 119 stars · 15 forks · 0 stars in 24 hours · Trending score 0.00

  9. 9
    Heman10x-NGU/openJev-verdict-2.0

    Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)

    GitHub · Python · 305 stars · 49 forks · 0 stars in 24 hours · Trending score 0.00

  10. 10
    intikhab49/open-jev-typed-decision-engine

    Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free. Trains on a Colab T4 in 30 min.

    GitHub · Python · 50 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00

  11. 11
    aovestdipaperino/laya-rust

    Pure-Rust inference for the Laya non-autoregressive typed-decision model (ModernBERT-large + RL decision head), on candle

    GitHub · Rust · 17 stars · 3 forks · 0 stars in 24 hours · Trending score 0.00

  12. 12
    Trystan-SA/laya-candle

    JEV-like Rust port using Laya, 100% local, no Python.

    GitHub · Rust · 10 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00

  13. 13
    tamnd/kime

    Typed decisions over text in milliseconds. A Rust inference engine and server that answers choice, score and yes or no questions with calibrated probabilities, compatible with Jev and Laya. The bar is 10x faster on every benchmark at equal or better accuracy.

    GitHub · Rust · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  14. 14
    Phocinae/Phocinae-Largha-150M-v1

    斑海豹 — Phocinae-Largha-150M-v1: a 144.3M bilingual decision model. Tiny model. Big decisions. 小海豹,大决断。

    GitHub · Python · 572 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00

  15. 15
    sileod/tasknet

    Easy modernBERT fine-tuning and multi-task learning

    GitHub · Jupyter Notebook · 66 stars · 8 forks · 0 stars in 24 hours · Trending score 0.00