| # Case Forge β HF Space runtime (Gradio app on ZeroGPU). | |
| # | |
| # App inference runs in-Space on ZeroGPU (free): base Qwen3-4B + the published LoRA, | |
| # merged at first GPU call, generating via transformers under @spaces.GPU. | |
| # Heavy/offline work (corpus generation, training, LoRA merge) runs on Modal β NOT here. | |
| gradio>=6 | |
| spaces # ZeroGPU (@spaces.GPU) β no-op locally | |
| transformers>=4.49 | |
| peft>=0.13 # load + merge_and_unload the adapter | |
| accelerate>=1 | |
| torch | |
| jsonschema>=4 # full structural validation of the output contract | |