Lauler

Lauler's Stars

• stanfordnlp/dspy

  DSPy: The framework for programming—not prompting—language models

  Language:Python20.5k1528901.5k

• Lightning-AI/litgpt

  20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

  Language:Python11k978151.1k

• outlines-dev/outlines

  Structured Text Generation

  Language:Python8.2k47553414

• jasonppy/VoiceCraft

  Zero-Shot Speech Editing and Text-to-Speech in the Wild

  Language:Jupyter Notebook7.8k89134758

• pytorch/torchtune

  PyTorch native post-training library

  Language:Python4.5k48804468

• mindee/doctr

  docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

  Language:Python4.1k43374457

• pytorch/torchtitan

  A native PyTorch Library for large model training

  Language:Python2.8k44198228

• unum-cloud/usearch

  Fast Open-Source Search & Clustering engine × for Vectors & 🔜 Strings × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍

  Language:C++2.4k29169151

• unum-cloud/ucall

  Web Serving and Remote Procedure Calls at 50x lower latency and 70x higher bandwidth than FastAPI, implementing JSON-RPC & REST over io_uring ☎️

  Language:C1.2k193044

• xhluca/bm25s

  Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy

  Language:Python95043644

• huggingface/lighteval

  Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

  Language:Python89930172109

• oh-my-ocr/text_renderer

  Language:Python806967162

• allenai/papermage

  library supporting NLP and CV research on scientific papers

  Language:Python721113657

• mlfoundations/open_lm

  A repository for research on medium sized language models.

  Language:Python481206769

• huggingface/cosmopedia

  Language:Python477111245

• NVIDIA/JAX-Toolbox

  JAX-Toolbox

  Language:Jupyter Notebook2692118250

• huggingface/diarizers

  Language:Python2645817

• rwitten/HighPerfLLMs2024

  Language:Python25114422

• ymy-k/Hi-SAM

  [TPAMI'24] Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation

  Language:Python227122016

• foundation-model-stack/fms-fsdp

  🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash attention v2.

  Language:Python206123532

• Kipok/NeMo-Skills

  A pipeline to improve skills of large language models

  Language:Python191103541

• ppaanngggg/layoutreader

  A Faster LayoutReader Model based on LayoutLMv3, Sort OCR bboxes to reading order.

  Language:Python1374108

• zh460045050/VQGAN-LC

  Language:Python1064116

• EleutherAI/improved-t5

  Experiments for efforts to train a new and improved t5

  Language:Python76625

• AnswerDotAI/bert24

  Language:Python7216284

• siyan-zhao/prepacking

  The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"

  Language:Jupyter Notebook57212

• h4pZ/h4rch

  My Arch dotfiles

  Language:Shell8100

• nikvaessen/w2v2-batch-size

  Code for paper "The effect of batch size on contrastive self-supervised speech representation learning"

  Language:Python8301

• swiss-ai/nanotron

  Minimalistic large language model 3D-parallelism training

  Language:Python7215

• swerik-project/the-swedish-parliament-corpus

  A repository for managing public, versioned releases of the Swedish Parliament Corpus.

  Language:Python55220