MinishLab / model2vecLinks
Fast State-of-the-Art Static Embeddings
☆1,990Updated last month
Alternatives and similar repositories for model2vec
Users that are interested in model2vec are comparing it to the libraries listed below
Sorting:
- Fast Multimodal Semantic Deduplication & Filtering☆879Updated last week
- A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.☆1,592Updated last month
- Bringing BERT into modernity via both architecture changes and scaling☆1,625Updated 7 months ago
- Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy☆1,473Updated this week
- Use late-interaction multi-modal models such as ColPali in just a few lines of code.☆841Updated last year
- Things you can do with the token embeddings of an LLM☆1,452Updated 2 months ago
- The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.☆2,476Updated 3 weeks ago
- Tool for generating high quality Synthetic datasets☆1,476Updated 3 months ago
- Fast, Accurate, Lightweight Python library to make State of the Art Embedding☆2,665Updated 3 weeks ago
- Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024☆2,737Updated this week
- Colivara is a suite of services that allows you to store, search, and retrieve documents based on their visual embedding. ColiVara has st…☆1,446Updated 9 months ago
- 🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL☆1,133Updated last week
- UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection☆1,101Updated last week
- 🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines☆3,693Updated this week
- Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cro…☆933Updated last month
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆3,684Updated 8 months ago
- A system for agentic LLM-powered data processing and ETL☆3,501Updated 2 weeks ago
- Late Interaction Models Training & Retrieval☆693Updated 3 weeks ago
- AI-Powered Data Processing: Use LOTUS to process all of your datasets with LLMs and embeddings. Enjoy up to 1000x speedups with fast, acc…☆1,537Updated last week
- Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-…☆3,839Updated 8 months ago
- Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali☆2,642Updated last month
- Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜☆1,865Updated 3 weeks ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,068Updated 2 weeks ago
- 🤗 Benchmark Large Language Models Reliably On Your Data☆425Updated last month
- ☆695Updated 9 months ago
- ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.☆1,480Updated 5 months ago
- A lightweight, local-first, and 🆓 experiment tracking library from Hugging Face 🤗☆1,234Updated last week
- Synthetic data curation for post-training and structured data extraction☆1,618Updated last week
- A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling.☆3,792Updated 3 weeks ago
- Cache-Augmented Generation: A Simple, Efficient Alternative to RAG☆1,464Updated 8 months ago