triple-Mu

triple-mu's starred repositories

PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

Language:PythonApache-2.039780 430 9033

clash-verge-rev

Continuation of Clash Verge - A Clash Meta GUI based on Tauri (Windows, MacOS, Linux)

Language:TypeScriptGPL-3.022853 86 1074

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

Language:Jupyter NotebookNOASSERTION19386 224 43

guidance

A guidance language for controlling large language models.

Language:Jupyter NotebookMIT17949 116 485

llm-cookbook

面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版

Language:Jupyter Notebook10129 83 31

mimalloc

mimalloc is a compact general purpose allocator with excellent performance.

Language:CMIT9648 159 587

Megatron-LM

Ongoing research training transformer models at scale

Language:PythonNOASSERTION9077 157 559

yolov10

YOLOv10: Real-Time End-to-End Object Detection

Language:PythonAGPL-3.07413 38 225

MiniCPM-V

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

Language:PythonApache-2.07190 74 225

lm-evaluation-harness

A framework for few-shot evaluation of language models.

Language:PythonMIT5557 36 888

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Language:PythonBSD-3-Clause5283 61 89

arrayfire

ArrayFire: a general purpose GPU library.

Language:C++BSD-3-Clause4444 150 1649

lmql

A language for constraint-guided and efficient LLM programming.

Language:PythonApache-2.03438 22 245

HunyuanDiT

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Language:PythonNOASSERTION2335 31 76

argh

Argh! A minimalist argument handler.

Language:C++BSD-3-Clause1300 19 51

YOLOv8-TensorRT

YOLOv8 using TensorRT accelerate !

Language:C++MIT1159 12 172

Skywork

Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc. 天工系列模型在3.2TB高质量多语言和代码数据上进行预训练。我们开源了模型参数，训练数据，评估数据，评估方法。

Language:PythonNOASSERTION1148 22 63

minisora

MiniSora: A community aims to explore the implementation path and future development direction of Sora.

Language:PythonApache-2.01073 17 62

advcpmv

A patch for GNU Core Utilities cp, mv to add progress bars

Language:Shell730 26 13

APISR

APISR: Anime Production Inspired Real-World Anime Super-Resolution (CVPR 2024)

Language:PythonGPL-3.0725 14 14

qwen.cpp

C++ implementation of Qwen-LM

Language:C++NOASSERTION500 9 72

TensorRT-Model-Optimizer

TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization and sparsity. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed on NVIDIA GPUs.

Language:PythonNOASSERTION250 8 24