Stars
A golang-based data loader which can be used from Python. Useful to interact with a typical VectorDB stack through HTTP requests and then fetch payloads per sample, at GB/s speeds.
[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild
A unified ensemble framework for PyTorch to improve the performance and robustness of your deep learning model.
An open-source & self-hostable Heroku / Netlify / Vercel alternative.
Tools for merging pretrained large language models.
A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
Extend existing LLMs way beyond the original training length with constant memory usage, without retraining
depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.
Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
Simplex Random Feature attention, in PyTorch
The robust text processing pipeline framework enabling customizable, efficient, and metric-logged text preprocessing.
A Python package for easy multiprocessing, but faster than multiprocessing
get things from one computer to another, safely
Code and Data for "Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering"
The only open-source toolkit that can download EDGAR financial reports and extract textual data from specific item sections into nice and clean JSON files.
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333
[IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution
talesofai / AnimateDiff
Forked from guoyww/AnimateDiffForked version of AnimateDiff, attempts to add init images. If you are look into original repo, please go to https://github.com/guoyww/animatediff/
WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)
文本挖掘和预处理工具(文本清洗、新词发现、情感分析、实体识别链接、关键词抽取、知识抽取、句法分析等),无监督或弱监督方法