Unofficial PyTorch/🤗Transformers(Gemma/Llama3) implementation of Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" (https://arxiv.org/abs/2404.07143)

Gemma 2B with 10M context length using Infini-attention.

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning

Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Finetune llama2-70b and codellama on MacBook Air without quantization

Python bindings for llama.cpp

A list of resources for hacking on the Rabbit r1

To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.

An AI search engine inspired by Perplexity

⚡FlashRAG: A Python Toolkit for Efficient RAG Research

☁️ Build multimodal AI applications with cloud-native stack

Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

A fast inference library for running LLMs locally on modern consumer-class GPUs

A Native-PyTorch Library for LLM Fine-tuning

Run python and pygame code in your html

🔍 AI search engine - self-host with local or cloud LLMs

Easily train a good VC model with voice data <= 10 mins!

아이유 노래 가사를 이용하여 랜덤 가사 생성

pip-installable binaries (wheels) for the extended version of the Hugo static site generator (note: unofficial, community-maintained)

LLM based autonomous agent that does online comprehensive research on any given topic

Web-based SQLite database browser written in Python

HTTP reverse proxy designed to facilitate secure access to HTTP services located within an internal network