LSC2204

dive-into-llms

《动手学大模型Dive into LLMs》系列编程实践教程

DPR

Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

recommenders

Best Practices on Recommendation Systems

YabyerChessEngine

Chess Engine + GUI

MarkdownSharp

Open source C# implementation of Markdown processor, used by Stack Overflow.

stack-overcloned

H2O

[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

llama3

The official Meta Llama 3 GitHub site

RDMI

This is the repo for remote direct memory introspection.

KIVI

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

cs229m_notes

ebooks

收藏的一些经典的历史、政治、心理、哲学、数学、计算机方面电子书(约10万本）

ChunkLlama

[ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"

LongBench

[ACL 2024] LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

text-generation-inference

Large Language Model Text Generation Inference

chronos-forecasting

Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting

GP-GAN

Official Chainer implementation of GP-GAN: Towards Realistic High-Resolution Image Blending (ACMMM 2019, oral)

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Inpaint-Anything

Inpaint anything using Segment Anything and inpainting models.

COMP646_Project

COMP 646 project at Rice in spring 2024

Time-LLM

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

Neural-Network-Parameter-Diffusion

We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard latent diffusion model to synthesize a new set of parameters

flash-attention

Fast and memory-efficient exact attention

LongLM

[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

system-design

A resource to help you pass system design interview and become good at work 👇

Open-Sora-Plan

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

LatexToMathML

Latex转Word格式的公式

Efficient-LLMs-Survey

[TMLR 2024] Efficient Large Language Models: A Survey

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

llmtime