gatilin/nanoVLM-222M-webui

docs: update README Space URLs to gatilin deployment

fix: tokenizer special token addition + 222M mp_image_token_length autocompute

fix: avoid tokenizers.Encoding type issue by using tokenize=False + encode()

fix: cap patch grid to 8x8 for 222M model compat

fix: ensure DynamicResize output is divisible by patch_size

fix: Gradio 6.0 compat + 222M model config field

fix(Dockerfile): replace libgl1-mesa-glx with libgl1 for Debian trixie compat

fix: add HF Spaces YAML frontmatter to README.md

feat: add nanoVLM-222M Web UI for Hugging Face Spaces

initial commit