rogerdehe

manim

Animation engine for explanatory math videos

awesome-wechat-weapp

微信小程序开发资源汇总 :100:

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

PlotNeuralNet

Latex code for making neural networks diagrams

manim

A community-maintained Python framework for creating mathematical animations.

GPT_API_free

Free ChatGPT API Key，免费ChatGPT API，支持GPT4 API（免费），ChatGPT国内可用免费转发API，直连无需代理。可以搭配ChatBox等软件/插件使用，极大降低接口使用成本。国内即可无限制畅快聊天。

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

flash-attention

Fast and memory-efficient exact attention

wandb

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

openai-node

The official Node.js / Typescript library for the OpenAI API

DeepSpeedExamples

Example models using DeepSpeed

Firefly

Firefly: 大模型训练工具，支持训练Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

alive-progress

A new kind of Progress Bar, with real-time throughput, ETA, and very cool animations!

pyjwt

JSON Web Token implementation in Python

tortoise-orm

Familiar asyncio ORM for python, built with relations in mind

mellow

Mellow is a rule-based global transparent proxy client for Windows, macOS and Linux. Also a Proxifier alternative.

nccl

Optimized primitives for collective multi-GPU communication

MTBook

《机器翻译：基础与模型》肖桐 朱靖波 著 - Machine Translation: Foundations and Models

gino

GINO Is Not ORM - a Python asyncio ORM on SQLAlchemy core.

ManimML

ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library.

weapp-wechat-zhihu

微信中的知乎--微信小程序 demo // Zhihu in Wechat

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

python-jose

A JOSE implementation in Python

Paper-Picture-Writing-Code

MLNLP: Paper Picture Writing Code

whoosh

Pure-Python full-text search library

ContextualSP

Multiple paper open-source codes of the Microsoft Research Asia DKI group

document-ai-transformers

stable-diffusion-webui-visualize-cross-attention-extension