Large Concept Models: Language modeling in a sentence representation space

PyTorch native post-training library

PyTorch per step fault tolerance (actively under development)

Bringing BERT into modernity via both architecture changes and scaling

Dataset and code for paper: "Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese".

[SIGIR'24] Generative Retrieval as Multi-Vector Dense Retrieval

SGLang is a fast serving framework for large language models and vision language models.

A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search sc…

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

SPLADE: sparse neural search (SIGIR21, SIGIR22)

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Official repository of the xLSTM.

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

An Efficient Transfer Learning Based Configuration Adviser for Database Tuning

This is the github repo for our CoLM 2024 paper "Beyond Relevance: Evaluate and Improve Retrievers on Perspective Awareness".

PyTorch Extension Library of Optimized Scatter Operations

XTR: Rethinking the Role of Token Retrieval in Multi-Vector Retrieval

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models(NeurIPS 2024 Spotlight)

Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors at once; across one or thousands of GPUs.

[ACL 2021] Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval Learns Passage Retrieval, Too https://arxiv.org/abs/2012.12624

CLIR version of ColBERT

A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM