A modular graph-based Retrieval-Augmented Generation (RAG) system

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.

Supercharge Your Model Training

A playbook for systematically maximizing the performance of deep learning models.

All-in-one text de-duplication

Python package for lexicon; Trie and DAWG implementation.

A Collection of BM25 Algorithms in Python

RAG AutoML Tool - Find optimal RAG pipeline for your own data.

Chat with your own data - LLM+RAG workshop

AutoPhrase: Automated Phrase Mining from Massive Text Corpora

Evaluate your LLM's response with Prometheus and GPT4 💯

Fine-Tuning Embedding for RAG with Synthetic Data

Model interpretability and understanding for PyTorch

Universal and Transferable Attacks on Aligned Language Models

Lazy Predict help build a lot of basic models without much code and helps understand which models works better without any parameter tuning

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

System design patterns for machine learning

An open collection of methodologies to help with successful training of large language models.

Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

A guidance language for controlling large language models.

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.

Come join the best place on the internet to learn AI skills. Use code "chatbotui" for an extra 20% off.

All the resources you need to get to Senior Engineer and beyond

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

A curated list of Large Language Model (LLM) Interpretability resources.

Probabilistic properties of language

The tiniest sentence encoder for Russian language

A blazing fast inference solution for text embeddings models