Advanced Quantization Algorithm for LLMs/VLMs. This is official implementation of "Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs"

Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ

This repository contains an implementation of the LLaMA 2 (Large Language Model Meta AI) model, a Generative Pretrained Transformer (GPT) variant. The implementation focuses on the model architectu…

Book of Elementary Functional Algorithms and Data structures

latex code from my first year of engineering.

Tips for Writing a Research Paper using LaTeX

Official inference framework for 1-bit LLMs

A flexible distributed key-value datastore that is optimized for caching and other realtime workloads.

This repo is for my lecture notes in Latex

A smaller subset of 10 easily classified classes from Imagenet, and a little more French

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

CLIP-like model evaluation

BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

An open source implementation of CLIP.

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

LLM Quantization toolkit

Collections of awesome neovim plugins.

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

Generates LaTeX document

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

3d extension to ggplot

[EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit".

R's data.table package extends data.frame:

Open-source scientific and technical publishing system built on Pandoc.

re-typeset of this book

Additional exercises and data for EE364a. No solutions; for public consumption.

SGLang is a fast serving framework for large language models and vision language models.

百鸟朝凤 · 肖江虹（精排版）

Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)