Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"
- adapters
- fine-tuning
- large-language-models
- parameter-efficient
134,212 visible repositories in the index
2,017–2,040 of 4,889 · Most stars
Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"
Python programming for Nintendo 8 bits
DTW (Dynamic Time Warping) python module
Python based backdoor that uses Gmail to exfiltrate data through attachment. This RAT will help during red team engagements to backdoor any Windows machines. It tracks the user activity using screen capture and sends it to an attacker as an e-mail attachment.
一个好用的哔哩哔哩漫画下载器,拥有图形界面,支持关键词搜索漫画和二维码登入,黑科技下载未解锁章节,多线程下载,多种保存格式,本地漫画管理,一键检查更新!
Adds linux GUI application menu to a windows toolbar
https://wavespeed.ai/ [WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.
Download music from Deezer with a nice front end
An open-source Mathematica Kernel. This repository contains the Python modules for WL Built-in functions, variables, core primitives, e.g. Symbol, a parser to create Expressions, and an evaluator to execute them.
[ICML 2026] WorldMirror: Fast and Universal 3D reconstruction model for versatile tasks
The repository host gives no description.
An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.
Anomaly Detection and Correlation library
PDEBench: An Extensive Benchmark for Scientific Machine Learning
Evolutionary Algorithm using Python, 莫烦Python 中文AI教学
SoulX-FlashHead: A unified 1.3B-parameter framework designed for high-fidelity, infinite-length, and real-time streaming portrait video generation.
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
ᕲ Duino-Coin is a coin that can be mined with almost everything, including Arduino boards.
Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!
[NeurIPS'24 Spotlight, ICLR'25, ICML'25] 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.
Automatically create and populate albums in Immich from a folder structure in external libraries
:milky_way: Open Source AI for large scale open ended feedback
Full-color flat FDM printing with calibrated filament layer mixing. Reproduce image colors and tonal detail, fine-tune local recipes, and export slicer-ready 3MF files.
A tiny library for coding with large language models.