Fetching metadata from the HF Docker repository...
-
Add guardrails to reveal model call
-
Increase start story temperature and add opening lenses
-
Fix start story prompt
-
Fix continue story prompt
-
Fix LLM output guardrails
-
Add note & local run proof
-
Clean up code
-
Prevent shape judgment model thinking
-
Revise ollama & hf deployment to llama.cpp
-
Update ZeroGPU function duration
-
Fix ZeroGPU decorator
-
Fix CUDA libs
-
Add CUDA libs for llama.cpp
-
Add llama.cpp for shape model
-
Add panning to painting reveal
-
Fix HF model pipeline load
-
Fix torch_dtype, enhance painter prompt & generator
-
Add posture & gesture to shapes; add SFX to shape choice and shape color reveal
-
Improve shape card, fix shape card title, fix background
-
Add shape card for reveal & painting
-
Add material to shape
-
Add modal backend for shape reasoning model
-
ZeroGPU fix attempt
-
Clean up code
-
Add is_torch_fx_available fix for loading MiniCPM4.1-8B
-
Add ZeroGPU support
-
Initial push
