s-smits / modernbert-finetuneView external linksLinks
Fine-tune ModernBERT with custom tokenizers, curriculum learning, and next-gen optimizers.
☆74Jan 16, 2026Updated last month
Alternatives and similar repositories for modernbert-finetune
Users that are interested in modernbert-finetune are comparing it to the libraries listed below
Sorting:
- utilities for loading and running text embeddings with onnx☆45Aug 16, 2025Updated 6 months ago
- A massively multilingual modern encoder language model☆127Jan 20, 2026Updated 3 weeks ago
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆77Updated this week
- ☆16Jan 31, 2025Updated last year
- Library for evaluating RAG using Nuclia's models☆18Jul 31, 2024Updated last year
- Bringing BERT into modernity via both architecture changes and scaling☆1,630Jun 30, 2025Updated 7 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆150Jan 7, 2026Updated last month
- Further developed as SyntaxDot: https://github.com/tensordot/syntaxdot☆13Dec 18, 2020Updated 5 years ago
- Fast search index for SPLADE sparse retrieval models implemented in Python using Numpy and Numba☆34Oct 16, 2025Updated 4 months ago
- Bootstrap a server from llama-cpp in a few lines of python☆12Jul 6, 2024Updated last year
- Tiny evaluation of leading LLMs on competitive programming problems☆14Nov 28, 2024Updated last year
- Pre-train Static Word Embeddings☆94Sep 9, 2025Updated 5 months ago
- A Python implementation of an agent swarm system that works with local LLM servers. The system allows you to create multiple agents that …☆11Nov 20, 2024Updated last year
- YASEM - Yet Another Splade|Sparse Embedder - A simple and efficient library for SPLADE embeddings☆13May 22, 2025Updated 8 months ago
- NOAH's Corpus: Part-of-Speech Tagging for Swiss German☆12Jan 6, 2023Updated 3 years ago
- BERT&RoBERTa预训练代码，tensorflow和torch两种版本实现☆13Feb 8, 2023Updated 3 years ago
- Use spaCy for NLP and output to the FoLiA XML format.☆12Feb 27, 2024Updated last year
- This repository contains the training and evaluation code for llm-jp-modernbert-base.☆15Jun 17, 2025Updated 7 months ago
- ☆33Nov 21, 2025Updated 2 months ago
- MLX binary vectors and associated algorithms.☆14Mar 13, 2025Updated 11 months ago
- 🤖 Complete reproduction of 'AlphaGo Moment for Model Architecture Discovery' using MLX-LM instead of GPT-4. Autonomous neural architectu…☆27Jul 27, 2025Updated 6 months ago
- Implementation of ModernBERT in MLX☆20Jan 7, 2026Updated last month
- Tool for converting LLMs from uni-directional to bi-directional by removing causal mask for tasks like classification and sentence embedd…☆63Dec 12, 2024Updated last year
- Using short models to classify long texts☆21Mar 8, 2023Updated 2 years ago
- Official implementation of the ICML 2024 paper RoSA (Robust Adaptation)☆44Feb 13, 2024Updated 2 years ago
- Coreference resolution for German☆16Jun 26, 2017Updated 8 years ago
- A natural language processing tool for automatically detecting quotations in text.☆15Feb 26, 2022Updated 3 years ago
- alternative way to calculating self attention☆18May 25, 2024Updated last year
- ☆24Nov 19, 2024Updated last year
- ☆11Updated this week
- sequence tagging with spaCy and crfsuite☆20Mar 18, 2023Updated 2 years ago
- Smart commit messages☆18Oct 25, 2024Updated last year
- Expert annotated Hallmarks of Cancer Corpus☆21Sep 18, 2018Updated 7 years ago
- YAST - Yet Another SPLADE or Sparse Trainer☆21Jun 16, 2025Updated 8 months ago
- An advanced AI-powered conversational agent leveraging the Llama 3.2 model and Phidata framework. Features include reasoning, natural lan…☆16Oct 29, 2024Updated last year
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆85Aug 20, 2025Updated 5 months ago
- FormFill is a CLI tool that uses LLMs to automatically fill out PDF forms.☆29Nov 22, 2024Updated last year
- Unattended Lightweight Text Classifiers with LLM Embeddings☆186Sep 6, 2024Updated last year
- Qwen-WisdomVast is a large model trained on 1 million high-quality Chinese multi-turn SFT data, 200,000 English multi-turn SFT data, and …☆18Apr 12, 2024Updated last year