🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
- adapter
- diffusion
- llm
- parameter-efficient-learning
47,133 repositories indexed
25–48 of 245 · Most stars
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Translated⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. A lightweight AI algorithm for making ID photos.
An efficient, small mobile key-value storage framework developed by WeChat. Works on Android, iOS, macOS, Windows, POSIX, and OHOS.
Nim is a statically typed compiled systems programming language. It combines successful concepts from mature languages like Python, Ada and Modula. Its design focuses on efficiency, expressiveness, and elegance (in that order of priority).
React components for efficiently rendering large lists and tabular data
Translated🎬 卡卡字幕助手 (Kaka Subtitle Assistant) | VideoCaptioner - An intelligent LLM-based subtitle assistant - handles the full workflow of video subtitle generation, sentence segmentation, correction, and subtitle translation! - A powered tool for easy and efficient video subtitling.
Efficient Augmented Reality for the Web - 60fps on mobile!
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
[CVPR 2023] SadTalker:Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
Simple, reliable, and efficient distributed task queue in Go
TranslatedLuban 2(鲁班 2) —— An efficient and concise Android image compression library that closely replicates the compression strategy of WeChat Moments.
Simple, efficient background processing for Ruby
A powerful framework for faster, easier, and more efficient project development.
FlashMLA: Efficient Multi-head Latent Attention Kernels
A command-line productivity tool powered by AI large language models like GPT-5, will help you accomplish your tasks faster and more efficiently.
Minimal and efficient cross-platform file watching library
Provides an efficient allocation free async/await integration for Unity.
The official, opinionated, batteries-included toolset for efficient Redux development
QLoRA: Efficient Finetuning of Quantized LLMs
A JavaScript library for efficient data fetching
TranslatedImplement a minimal vue3 model ( Help you learn more efficiently vue3 source code )
concurrent, cache-efficient, and Dockerfile-agnostic builder toolkit
An alternative privacy-friendly YouTube frontend which is efficient by design.
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.