Fix README content mapping

Fix build indentation and enforce CUDA-only path

Repair README content and re-sync Space files

Add strict CUDA validation and CUDA-only runtime docs

Hardened precheck and runtime recovery

Update gradio version for runtime import compatibility

Compatibility fixes for local OCR models

Add cyttic OCR models to registry

Use local ZeroGPU offline inference only

Add PaddleOCR + DeepSeek OCR models and raise default output token budget

Scope GPU lease to active inference runs

Remove persistent GPU warmup; rely on sleep timeout for idle GPU control

Add compute-mode scheduling docs and final notes

ZeroGPU compute-mode scheduling + safety caps

Restore Gradio runtime with GRADIO_SHARE-safe launch and template compatibility patch

Switch Space UI to Streamlit to avoid gradio runtime errors on zero-a10g

Fix runtime dependency compatibility and add Nemotron-OCR-v2

Add Qwen3-VL 4B and 30B-A3B thinking/instruct variants

Move HF card metadata to repo frontmatter

Adjust app prompts for Hebrew printed+handwritten OCR focus

Upload Hebrew OCR comparison Space (printed + handwritten Hebrew OCR benchmark)

initial commit