QuantizedLSTM

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

AiLearning：数据分析+机器学习实战+线性代数+PyTorch+NLTK+TF2

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

A neural network that transforms a design mock-up into a static website.

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

Friendly machine learning for the web! ?

Lossy PNG compressor — pngquant command based on libimagequant library

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

中文古诗自动作诗机器人，x炸天，基于tensorflow1.10 api，正在积极维护升级中，快star，保持更新！