Personal collection of notebooks, Python scripts, and experimental work focused on deep learning and machine learning model architectures. It serves as a sandbox for trying out ideas, reproducing papers, building custom layers, and refining approaches to tasks such as classification, ranking, and generative modeling.
model_02102024_attn.py: Attention block + Linear layermodel_05122024_qwen_chatbot_setup.py: Framework to deploy llm as chatbot with qwen model
Contain workbooks on random hybrid models and insights completed in my spare time.