Update app.py

app.py

@@ -138,7 +138,7 @@ def infer(
     attention_mask = encoded_inputs["attention_mask"].to(device)
     print("-- tokenize prompt --")
       # Google T5
-    input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
+    #input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
     outputs = model.generate(
         input_ids=input_ids,
         attention_mask=attention_mask,
@@ -150,7 +150,6 @@ def infer(
     # Use the encoded tensor 'text_inputs' here
     enhanced_prompt = tokenizer.decode(outputs[0], skip_special_tokens=True)
     print('-- generated prompt --')
-    print(enhanced_prompt)
     enhanced_prompt = filter_text(enhanced_prompt,prompt)
     print('-- filtered prompt --')
     print(enhanced_prompt)