PyGraphistry is a Python library to quickly load, shape, embed, and explore big graphs with the GPU-accelerated Graphistry visual graph analyzer

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Quantized Attention that achieves speedups of 2.1x and 2.7x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

Code and datasets for "The Hard Positive Truth about Vision-Language Compositionality" at ECCV 2024.

Code for paper RAVE: Residual Vector Embedding for CLIP-Guided Backlit Image Enhancement

Multi-page document understanding and VQA using OCR-free method

Aggregation framework for annotating datasets in computer vision tasks (detection, segmentation, video captioning etc.)

DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Models

Docker files for a dockerized unoserver

Universal Office Converter - Convert between any document format supported by LibreOffice/OpenOffice.

A Toolkit for Table-based Question Answering

We collect papers about "large language models (LLM) for table-related tasks", e.g., using LLM for Table QA task. “表格+LLM”相关论文整理

A large annotated semantic parsing corpus for developing natural language interfaces.

Ontology for real world section id data

Neovim config for the lazy

Vary-tiny codebase upon LAVIS （for training from scratch）and a PDF image-text pairs data (about 600k including English/Chinese)

Official Repository of ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning

[ACM'MM 2024 Oral] Official code for "OneChart: Purify the Chart Structural Extraction via One Auxiliary Token"

QLoRA: Efficient Finetuning of Quantized LLMs

ONNX Serving is a project written with C++ to serve onnx-mlir compiled models with GRPC and other protocols.Benefiting from C++ implementation, ONNX Serving has very low latency overhead and high t…

Datasette tutorial. Calculate and query embeddings on 5,000 rows in a sqlite database.

A toolkit for building multimodal AI agents

Baselines for all tasks from Long Code Arena benchmarks 🏟️

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Free and Open Source, Distributed, RESTful Search Engine

Code release for Hu et al. Learning to Reason: End-to-End Module Networks for Visual Question Answering. in ICCV, 2017

fault-tolerant Python3 package for searching, navigating, and modifying LaTeX documents