transformers

Pytorch Code for the paper TransWeather - CVPR 2022

[CVPR 2024] Official implementation of the paper "Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement"

[NeurIPS 2025] Native-resolution diffusion Transformer

PyTorch Implementation of CvT: Introducing Convolutions to Vision Transformers

OCR, Archive, Index and Search: Implementation agnostic OCR framework.

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.

[MedIA Journal] An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"

Official Implementation of SegFormer3D: an Efficient Transformer for 3D Medical Image Segmentation (CVPR 2024)

A python package for benchmarking interpretability techniques on Transformers.

Prompt Engineering Jumpstart: The simplest beginner's guide to talking with AI. Learn universal prompt engineering principles with simple analogies & copy-paste examples for ChatGPT & DALL-E. No tech skills needed. Free, open-source eBook.

Deploy BERT for Sentiment Analysis as REST API using FastAPI, Transformers by Hugging Face and PyTorch

This repository contains all the work that I regularly did and studied from Medium blogs, several research papers, and other Repos (related/unrelated to the research papers).

Easy and lightning fast training of 🤗 Transformers on Habana Gaudi processor (HPU)

Implementation of Danijar's latest iteration for his Dreamer line of work

PyTorch code for "VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks" (CVPR2022)

OpenTextClassification is all you need for text classification! Open text classification for everyone, enjoy your NLP journey! 这可能是目前为止最全面的开源文本分类项目，支持中英双语、多种模型、多种任务。

KoBERT on 🤗 Huggingface Transformers 🤗 (with Bug Fixed)

pretrained BERT model for cyber security text, learned CyberSecurity Knowledge

[CVPR 2025 (Oral)] Open implementation of "RandAR"