fix stream output

app.py

@@ -35,22 +35,13 @@ def chat(user_input, max_new_tokens=512):
     thread = Thread(target=generate)
     thread.start()
 
+    prompt_len = len(prompt)
     generated_text = ""
     for new_text in streamer:
         generated_text += new_text
-        yield generated_text
+        yield generated_text[prompt_len:]
 
     thread.join()
-    
-    # generate response
-    #with torch.no_grad():
-    #    outputs = model.generate(
-    #        **inputs,
-    #        max_new_tokens=max_new_tokens,
-    #        pad_token_id=tokenizer.eos_token_id
-    #    )
-    #response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[-1]:], skip_special_tokens=True)
-    #return response
 
 # Construct Gradio Interface
 interface = gr.Interface(