Stars
SGLang is a fast serving framework for large language models and vision language models.
Fully open reproduction of DeepSeek-R1
A course on aligning smol models.
Everything about the SmolLM and SmolVLM family of models
Code for the curation of The Stack v2 and StarCoder2 training data
Large Language Model Text Generation Inference
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Lightweight and efficient entity linking model using transformer architecture.
[ECCV] Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration. Advances in Image Manipulation (AIM) workshop ECCV 2022. Try it out! over 3.3M runs https://replicate.com/m…
The official Python client for the Hugging Face Hub.
Official Pytorch implementation for HNeRV: a hybrid video neural representation (CVPR 2023)
This project is for DLSN introduced in the following paper "Global Learnable Attention for Single Image Super-Resolution".
A tool for refurbishing and modernizing Python codebases
Diffusion attentive attribution maps for interpreting Stable Diffusion.
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
PyTorch implementation of "Reference-based Image Super-Resolution with Deformable Attention Transformer (ECCV2022)"
Official PyTorch Code and Models of "RePaint: Inpainting using Denoising Diffusion Probabilistic Models", CVPR 2022
📝 Utility to create, edit, and publish model cards on the Hugging Face Hub. [**Now lives in huggingface_hub**]
Karras et al. (2022) diffusion models for PyTorch
Scripts to convert datasets from various sources to Hugging Face Datasets.
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]
A collection of resources and papers on Diffusion Models
Tools for handling multimodal data in machine learning projects.