Create app.py

app.py

@@ -0,0 +1,17 @@
+import gradio as gr
+from transformers import T5ForConditionalGeneration, RobertaTokenizer
+
+# Load the quantized model and tokenizer from Hugging Face Hub
+quantized_model = T5ForConditionalGeneration.from_pretrained("AbdulHadi806/codet5-finetuned-latest-quantized")
+tokenizer = RobertaTokenizer.from_pretrained("AbdulHadi806/codet5-finetuned-latest-quantized")
+
+def inference(input_text):
+    inputs = tokenizer(input_text, return_tensors="pt")
+    outputs = quantized_model.generate(**inputs)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Create Gradio interface
+iface = gr.Interface(fn=inference, inputs="text", outputs="text")
+
+# Launch the interface
+iface.launch()