LlamaIndex is the leading framework for building LLM-powered agents over your data.

仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理

pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models

The Model Zoo of Knowledge Tracing Models

A collection of Knowledge Tracing model implementations with PyTorch

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

This repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (STF). These papers are mainly categorized according to the …

Word, Excel, and PowerPoint plugin for QuickLook.

21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

"Pooling And Attention: What Are Effective Designs For LLM-Based Embedding Models?"

A modern ebook manager and reader with sync and backup capacities for Windows, macOS, Linux and Web

MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

MTEB: Massive Text Embedding Benchmark

逃离996

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

ESWA - Expert Systems with Applications latex template

Lime: Explaining the predictions of any machine learning classifier

A convenient way to link, deduplicate, aggregate and cluster data(frames) in Python using deep learning

Code for the paper "CollaborEM: A Self-supervised Entity Matching Framework Using Multi-features Collaboration". TKDE 2021.

Implementation of the paper "Deep Indexed Active Learning for Matching Heterogeneous Entity Representations"

Code for the paper "PromptEM: Prompt-tuning for Low-resource Generalized Entity Matching". VLDB 2023.

WInte.r is a Java framework for end-to-end data integration. The WInte.r framework implements well-known methods for data pre-processing, schema matching, identity resolution, data fusion, and resu…

A collection of awesome resources regarding Record Linkage.

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples

The implementation of DeBERTa

The dataset for the paper "Machamp: A Generalized Entity Matching Benchmark" published in CIKM 2021