nlp

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

🦅 Pretrained BigBird Model for Korean (up to 4096 tokens)

A guided tour on how to use HuggingFace large language models on Macs with Apple Silicon

🗺️ Data Cleaning and Textual Data Visualization 🗺️

Full-stack open-source AI engine for building language models — tokenizer training, transformer architecture, cognitive reasoning and chat pipeline.

pgvector for PostgreSQL Windows (native compiled in Microsoft Windows environment)

Simple State-of-the-Art BERT-Based Sentence Classification with Keras / TensorFlow 2. Built with HuggingFace's Transformers.

A guide to LLM hacking: fundamentals, prompt injection, offense, and defense

Datasets collection and preprocessings framework for NLP extreme multitask learning

从 MiniMind 源码读起,再延伸到现代大模型技术体系的中文学习笔记。主线逐行精读预训练 / SFT / DPO / PPO / GRPO 与训练机制;附录 17 篇进阶卷覆盖量化、投机解码、RLHF 全景、模型代际史等 MiniMind 没涉及、但进阶绕不开的主题。

WritingBench: A Comprehensive Benchmark for Generative Writing

Automatic Prompt Optimization Framework

Fiddler Auditor is a tool to evaluate language models.

Label data using HuggingFace's transformers and automatically get a prediction service

Utility for behavioral and representational analyses of Language Models

Curso práctico: NLP de cero a cien 🤗

Open language modeling toolkit based on PyTorch

A codebase that makes differentially private training of transformers easy.

The "tl;dr" on a few notable transformer papers (pre-2022).

Comprehensive NLP Evaluation System