Unified project structure: app_space.py for ZeroGPU, root README metadata

Sync backends: Fix infinite loop and prompt echo

Initial commit: Production-ready OCR with PyTorch and GGUF backends

feat: Manually construct the prompt string instead of using `apply_chat_template` and add a `repetition_penalty` to generation arguments.

feat: Add repetition penalty to generation parameters and update default PDF scale slider value.

feat: Remove temperature parameter and slider, forcing greedy search (temperature=0.0) for OCR processing.

feat: remove temperature parameter from UI and hardcode inference temperature to 0.0

feat: Refactor `model.generate` parameters into `gen_kwargs` and add post-processing to remove the instruction prompt from generated text.

feat: Add Hugging Face Space demo with GGUF and PyTorch backends and update core application files and requirements.

feat: update ggml kernels, webui components, model templates, and build configurations

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Create requirements.txt

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

initial commit

Duplicate from gradio-templates/chatbot