This hands-on lab aims to alleviate some of that headache by demonstrating how to create/augment a QnA dataset from complex unstructured data, assuming a real-world scenario. The sample aims to be …

This lab is a 1-day/2-day end-to-end SLM workshop led and developed by AI GBB. Attendees will learn how to quickly and easily perform the data preparation-fine tuning-serving-LLMOps series of proce…

A Comprehensive Toolkit for High-Quality PDF Content Extraction

Omnivore is a complete, open source read-it-later solution for people who like reading.

One-click deploy of a Knowledge Graph powered RAG (GraphRAG) in Azure

Benchmarking PDF libraries

Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy

Tools for merging pretrained large language models.

The evaluation scripts of JMTEB (Japanese Massive Text Embedding Benchmark)

Convert PDF to markdown quickly with high accuracy

SpaCyEx allows the creation of spaCy Matcher patterns with RegEx like syntax.

A pytorch quantization backend for optimum

Train Models Contrastively in Pytorch

ReFT: Representation Finetuning for Language Models

A pure-python PDF library capable of splitting, merging, cropping, and transforming the pages of PDF files

Implementation of "Efficient Multi-vector Dense Retrieval with Bit Vectors", ECIR 2024

Interactively explore unstructured datasets from your dataframe.

https://graphacademy.neo4j.com/courses/llm-fundamentals/

Extraction of the journalistic five W and one H questions (5W1H) from news articles: who did what, when, where, why, and how?

The all-in-one solution for RAG. Build, scale, and deploy state of the art Retrieval-Augmented Generation applications

minimal pytorch implementation of bm25 (with sparse tensors)

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

A framework for prompt tuning using Intent-based Prompt Calibration

Open-source AI cookbook

Generative Representational Instruction Tuning

OCR, layout analysis, reading order, table recognition in 90+ languages

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: …

Educational materials on deep learning by Weights & Biases

Superfast AI decision making and intelligent processing of multi-modal data.