nanguoyu

EdgeDeviceLLMCompetition-Starting-Kit

ChatTTS

A generative speech model for daily dialogue.

ffcv

FFCV: Fast Forward Computer Vision (and other ML workloads!)

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Iterative-Feature-Merging

Official implementation of the "GOING BEYOND NEURAL NETWORK FEATURE SIMILARITY: THE NETWORK FEATURE COMPLEXITY AND ITS INTERPRETATION USING CATEGORY THEORY", ICLR2024

torchist

NumPy-style histograms in PyTorch

coremltools

Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.

QuickRecorder

A lightweight screen recorder based on ScreenCapture Kit for macOS / 基于 ScreenCapture Kit 的轻量化多功能 macOS 录屏工具

marker-api

Easily deployable 🚀 API to convert PDF to markdown quickly with high accuracy.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

stb

stb single-file public domain libraries for C/C++

git-re-basin-pytorch

Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch

corenet

CoreNet: A library for training deep neural networks

Queryable

Run OpenAI's CLIP model on iOS to search photos.

LLMs-from-scratch

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

vhs

Your CLI home video recorder 📼

mlx-examples

Examples in the MLX framework

knowtate

Knowtate is a sophisticated platform designed to elevate your academic research experience. Seamlessly blend reading, note-taking with notion style rich text editor, markdown, and excalidraw, and knowledge management into one intuitive interface, allowing you to effortlessly track your insights and ideas as you delve into scholarly literature.

BeamerPresenter

Modular multi-screen pdf presentation viewer

windows

Windows inside a Docker container.

neko

A self hosted virtual browser that runs in docker and uses WebRTC.

calculate-flops.pytorch

The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model)

Stirling-PDF

#1 Locally hosted web application that allows you to perform various operations on PDF files

mlx

MLX: An array framework for Apple silicon

UltraFastBERT

The repository for the code of the UltraFastBERT paper

ollama

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

tldraw

SDK for creating whiteboards and canvas experiences on the web.

llama4micro

A "large" language model running on a microcontroller

Yi

A series of large language models trained from scratch by developers @01-ai

SciencePlots

Matplotlib styles for scientific plotting