Add data folder with figures and demo

Add comprehensive model card and documentation

Add model_config.yaml: Model architecture and training configuration

Add tokenizer_config.json: Tokenizer configuration parameters

Add tokenizer.json: Tokenizer vocabulary and configuration

Add ViT-B-32.pt: Vision Transformer weights for image encoding

Add small.pt: Compressed model checkpoint

Add lit_model.pth: Main LitGPT model weights

initial commit