WHaverals
Follow
Stars
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
An e-paper dashboard for a Raspberry Pi Zero W.
A modular graph-based Retrieval-Augmented Generation (RAG) system
Use PEFT or Full-parameter to finetune 450+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 150+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, I…
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
Interpretability for sequence generation models 🐛 🔍
Validate and transform various OCR file formats (hOCR, ALTO, PAGE, FineReader)
Collection of tutorials for DeezyMatch (https://github.com/Living-with-machines/DeezyMatch)
A big list of homoglyphs and some code to detect them
Python tools for interacting with Wikidata
Fixes mojibake and other glitches in Unicode text, after the fact.
MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble and HNSW
Official code and data repository for our EMNLP 2020 long paper "Reformulating Unsupervised Style Transfer as Paraphrase Generation" (https://arxiv.org/abs/2010.05700).
Paper List for Style Transfer in Text
Everything you need to build state-of-the-art foundation models, end-to-end.
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
Letta (formerly MemGPT) is a framework for creating LLM services with memory.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Greatest Hits Versus Deep Cuts: Exploring Variety in Set-lists Across Artists and Musical Genres
A neural word aligner based on multilingual BERT
Multilingual sentence alignment using sentence embeddings
Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.