Deploy Qwen2.5 Coder 3B Gradio app

README.md

@@ -14,5 +14,5 @@ pinned: false
 A coding assistant using Qwen2.5-Coder-3B-Instruct with Hugging Face ZeroGPU.
 The model is downloaded from Hugging Face on first startup. Inference requests
 use the largest ZeroGPU allocation; xlarge requests consume twice the daily
-GPU quota of the default large size. The Python and model-library dependencies
-are pinned to versions supported by the ZeroGPU runtime.
+GPU quota of the default large size. Transformers and Hugging Face Hub versions
+are selected to remain compatible with the current Gradio ZeroGPU base image.

requirements.txt

@@ -1,2 +1,2 @@
-transformers==4.51.3
-huggingface-hub==0.36.2
+transformers==5.20.2
+huggingface-hub>=1.31.0,<3.0.0