Name: Nianhui Guo
Type: User
Company: Hasso Plattner Institute (HPI)
Bio: Ph.D student in Hasso Plattner Institute, Potsdam University, Germany. Mainly focusing on efficient deep neural network research.
Location: Potsdam, German
Nianhui Guo's Projects
Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf
Awesome LLM compression research papers and tools.
This is the Unofficial implementation of BiBERT paper
BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch
A toolkit enhances PyTorch with specialized functions for low-bit quantized neural networks.
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
Making big AI models cheaper, easier, and scalable
Acceptance rates for the major AI conferences
This repository contains the reference implementation for our proposed Convolutional CRFs.
Convolutional Neural Network with CUDA (MNIST 99.23%)
CUDA Templates for Linear Algebra Subroutines
深度学习面试宝典(含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向)
PyTorch Implementations of Dropout Variants
Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents
Official repository of Evolutionary Optimization of Model Merging Recipes
An implementation of EWC with PyTorch
Fast Hadamard transform in CUDA, with a PyTorch interface
The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
Structured Bayesian Pruning, NIPS 2017
An experiment with some brain-inspired ideas