General technology for enabling AI capabilities w/ LLMs and MLLMs

Lingvo

📃Language Model based sentences scoring library

ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward experts. We released a collection of ModuleFormer-based Language Models (MoLM) ranging in scale from 4 billion to 8 billion parameters.

ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations

TOEIC(Test of English for International Communication) solving using pytorch-pretrained-BERT model.

The LM Contamination Index is a manually created database of contamination evidences for LMs.

Korean text normalization and language preparation package for LM in Kaldi-based ASR system

🐍 Python library for n-gram models in ARPA format

Embeddings: State-of-the-art Text Representations for Natural Language Processing tasks, an initial version of library focus on the Polish Language

The official repo for "TheoremQA: A Theorem-driven Question Answering dataset" (EMNLP 2023)

Crackhash is a tool that try to crack different types of hashes using free online services.

ChatGPT learns automatically.

Make your Generative AI LM model from the scratch (Including pretraining / SFT with LoRA)

The code for "VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by VIdeo SpatioTemporal Augmentation" [CVPR2025]

Simple and modern webui for LLM models based LLaMA.

The Slick license manager, a powerful and detailed license manager for the S Desktop Environment/SDE/Skeuowie

Use ntlm.pw to quickly and automatically convert hash dumps to credentials

Dummy implementations to explore the details and key aspects of schemes and protocols. Focused now on authentication schemes.

ASR pytorch project