hsiaolinhu

BiLLM

(ICML 2024) BiLLM: Pushing the Limit of Post-Training Quantization for LLMs

vimtex

VimTeX: A modern Vim and neovim filetype plugin for LaTeX files.

ustb_choose_course_system

【OUTDATED】北京科技大学选课系统第三方Windows、Linux、Mac、Android、iOS客户端

OpenFedLLM

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

UFO

A UI-Focused Agent for Windows OS Interaction.

QuantizedEmpirical

zotero-better-bibtex

Make Zotero effective for us LaTeX holdouts

jabref

Graphical Java application for managing BibTeX and biblatex (.bib) databases

reor

Private & local AI personal knowledge management app.

LWM

acl-style-files

Official style files for papers submitted to venues of the Association for Computational Linguistics

OLMo

Modeling, training, eval, and inference code for OLMo

DeepZero

[ICLR'24] "DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training" by Aochuan Chen*, Yimeng Zhang*, Jinghan Jia, James Diffenderfer, Jiancheng Liu, Konstantinos Parasyris, Yihua Zhang, Zheng Zhang, Bhavya Kailkhura, Sijia Liu

FedZO

Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learning

Hybrid-Decentralized-Optimization

The code for the paper "Hybrid Decentralized Optimization: First- and Zeroth-Order Optimizers Can Be Jointly Leveraged For Faster Convergence"

FwdLLM

BAFFLE

The official implement of paper "Does Federated Learning Really Need Backpropagation?"

CocktailSGD

topology-in-decentralized-learning

Code related to ’Beyond spectral gap: The role of the topology in decentralized learning‘.

Efficient_Foundation_Model_Survey

Survey Paper List - Efficient LLM and Foundation Models

QAnything

Question and Answer based on Anything.

Megatron-LLM

distributed trainer for LLMs

asyncdiloco

FedPepTAO

unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

punica

Serving multiple LoRA finetuned LLM as one

natural-instructions

Expanding natural instructions

BlueLM

BlueLM(蓝心大模型): Open large language models developed by vivo AI Lab

GreenTrainer

Code for paper "Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation" (ICLR'24)