Stars
Use late-interaction multi-modal models such as ColPali in just a few lines of code.
Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.
Provides a common interface to many IR ranking datasets.
A Python framework for performing information retrieval experiments, building on https://terrier.org/
A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.
🤖 The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transf…
⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍
A lightweight library for portable low-level GPU computation using WebGPU.
Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of GPT-Fast, a simple, PyTorch-native generation codebase.
Fast, Modern, Memory Efficient, and Low Precision PyTorch Optimizers
Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024
Training LLMs with QLoRA + FSDP
Official implementation of Half-Quadratic Quantization (HQQ)
JQaRA: Japanese Question Answering with Retrieval Augmentation - 検索拡張(RAG)評価のための日本語Q&Aデータセット
DSPy: The framework for programming—not prompting—foundation models
Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models, clip, clap and colpali
In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.
Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
Benchmark for Japanese document embedding & vector search
Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & C…