Update app.py

app.py

@@ -27,6 +27,7 @@ def load_model_and_tokenizer():
     )
     return model, tokenizer
 
+# Ensure the model and tokenizer are loaded
 model, tokenizer = load_model_and_tokenizer()
 
 # Generate Response
@@ -50,12 +51,13 @@ def generate_response(prompt, chat_history):
         top_k=50,
         top_p=0.95,
         temperature=0.7,
-        stream=True
+        output_scores=True,
+        return_dict_in_generate=True
     )
 
     response = ""
-    for new_token in generated_ids[0][len(model_inputs.input_ids[0]):]:
-        response += tokenizer.decode([new_token], skip_special_tokens=True)
+    for token_id in generated_ids.sequences[0][len(model_inputs.input_ids[0]):]:
+        response += tokenizer.decode([token_id], skip_special_tokens=True)
         yield response
 
 # Clear Chat History