🖤 Create and share beautiful images of your source code

[CVPR 2024 Best paper award candidate] EGTR: Extracting Graph from Transformer for Scene Graph Generation

Code for the Molmo Vision-Language Model

LLM2CLIP significantly improves already state-of-the-art CLIP models.

[ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"

A custom Huggingface trainer which supports logging auxiliary losses returned by your model

코레일의 매진된 기차표를 구할 수 있도록 도와주는 크롬 확장기능입니다.

TRACE: Table Reconstruction Aligned to Corner and Edges (ICDAR 2023)

CARTE: Cell Adjacency Relation for Table Evaluation

[ACL 2024] This is the code repo for our ACL’24 paper "Cleaner Pretraining Corpus Curation with Neural Web Scraping".

Line-by-line profiling for Python

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

LaVIT: Empower the Large Language Model to Understand and Generate Visual Content

Generative Models by Stability AI

The uncompromising Python code formatter

Code for the paper "Evaluating Large Language Models Trained on Code"

An open source implementation of CLIP.

Official Pytorch implementation of "Graphit: A Unified Framework for Diverse Image Editing Tasks"

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

High-Resolution Image Synthesis with Latent Diffusion Models

A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick

Official Implementation of Web-based Visual Corpus Builder (Webvicob), ICDAR 2023

Gated Recurrent Unit with a Decay mechanism for Multivariate Time Series with Missing Values