a containerized tool for scanning and reporting vulnerabilities in local or docker-based applications.

a character-level language model inspired by qwen3, implemented and trained on shakespeare dataset.

a lightweight character-level language model inspired after llama 3.2, trained on the shakespeare dataset.

an efficient character-level mixture-of-experts model inspired from qwen3-moe, trained on shakespeare.

a 4-bit quantized and instruction-tuned qwen3 model fine-tuned on custom data, that speaks yoda.

A RAG application built from the official langchain tutorial.