LJQ

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

A lightweight Python framework where an AI model controls your computer, browser, terminal, files, mouse and keyboard, and builds a personal skill library from each completed task so future similar tasks run faster.

A very simple GRPO implement for reproducing r1-like LLM thinking.

A Keras+TensorFlow Implementation of the Transformer: Attention Is All You Need

Low ReSource Reinforcement Learning with CPU Offloading Training Support

The API utils for querying CN-DBpedia & CN-Probase, the biggest Chinese knowledge bases

An easy-to-use BERT in keras via tf-hub.

Automatically find list items in a webpage

Pretrain own bert / roberta model with wwm-mlm and modified tokenizer (both chinese and english).

No description.

Auto-coloring for gray images

No description.

The Shadow Brokers "Lost In Translation" leak

Generative Adversarial Transformers