HF agents course error in duplicating my first agent

A Hugging Face agents course user encountered a runtime error when duplicating the first agent example on ZeroGPU, with the message 'No @spaces.GPU function detected during startup.' The fix involves adding an unused @spaces.GPU-decorated dummy function to app.py, adding a final_answer section to prompts.yaml, and recreating the HF_TOKEN secret, as ZeroGPU requires the decorator even though the LLM inference runs via Inference Providers, not on the Space GPU.

i tried to duplicate the agents example using zeroGPU cz it’s the free one , but i get this error runtime error Hmm… at first I thought, “Why ZeroGPU??” …but apparently with a Free account now, ZeroGPU is basically the only compute-backed Gradio option you can host yourself… I didn’t know that. The immediate error: No @spaces.GPU function detected during startup does not look like a smolagents or Qwen error. It is ZeroGPU rejecting the Space at startup because it cannot find a function decorated with @spaces.GPU . For this particular course template , I would take the minimal route first rather than trying to move the agent itself onto the GPU. Add this near the imports in app.py : python import spaces @spaces.GPU duration=1 def dummy gpu : return None and leave the function unused. The documented/intended ZeroGPU pattern is, of course, to decorate an actual GPU-dependent function; see the ZeroGPU documentation https://huggingface.co/docs/hub/spaces-zerogpu . The decorator causes a GPU to be allocated when the decorated function is called and released afterward. But this course agent does not actually need a Space GPU for its LLM inference , so I tested the unused dummy-decorator variant in a duplicated ZeroGPU Space, and it was enough to get past this startup check. I would also make one tiny preventive edit to prompts.yaml while you are there: "final answer": "pre messages": "" "post messages": "" Add that as a top-level section near the end of the file. And make sure that your duplicated Space has an HF TOKEN Secret with inference permission. Secrets are deliberately not copied into duplicated Spaces; the course itself asks you to recreate HF TOKEN https://huggingface.co/learn/agents-course/unit1/tutorial , and the For the smallest-change course path, I would therefore do only this initially: 1. Keep the template's smolagents==1.13.0 for now. 2. Add the unused @spaces.GPU dummy. 3. Add the three-line final answer section to prompts.yaml. 4. Recreate/check HF TOKEN. 5. Rebuild. I would not upgrade all of smolagents at the same time unless you actually want to modernize the template, because there is a separate version-drift problem hiding behind this one. The important conceptual warning is that getting the ZeroGPU Space to start does not mean that Qwen-32B is now running for free on ZeroGPU . Those are two different systems. ZeroGPU → hosts the Gradio Space / allocates GPU to @spaces.GPU calls InferenceClientModel → calls a remotely hosted model through Hugging Face Inference Providers The current course page https://huggingface.co/learn/agents-course/unit1/tutorial explicitly uses: model = InferenceClientModel max tokens=2096, temperature=0.5, model id="Qwen/Qwen2.5-Coder-32B-Instruct", custom role conversions=None, and describes Qwen2.5-Coder-32B-Instruct as being accessed through the serverless API. So there are really several independent traps layered on top of each other here. Why choosing ZeroGPU on a Free account actually makes sense nowSo my mental model for this particular failure would be: Trap 1: Free-account Space policy ↓ ZeroGPU becomes the practical free Gradio-hosting route Trap 2: ZeroGPU expects @spaces.GPU ↓ old course template has none ↓ "No @spaces.GPU function detected" Trap 3: getting ZeroGPU to start does NOT put Qwen-32B on ZeroGPU ↓ the LLM still uses Inference Providers ↓ separate inference credits / provider limits apply Trap 4: the current lesson and duplicate template have version drift ↓ HfApiModel vs InferenceClientModel smolagents 1.13.0 pin missing final answer prompt other migration differences For your immediate problem , though, I would not try to solve all four layers at once. I would start with just: python import spaces @spaces.GPU duration=1 def dummy gpu : return None plus: "final answer": "pre messages": "" "post messages": "" make sure HF TOKEN exists, and rebuild. If that starts, then the original ZeroGPU error is solved. Any error after that is much easier to classify as an inference/token/provider issue or as the separate template-version issue above, rather than one giant mysterious Space failure.