Update app.py

app.py

@@ -14,11 +14,11 @@ print(time_load_model_start)
 # Load the model and tokenizer outside of the functions
 llm = pipeline("text-generation",
                 model=my_config['model_name'],
-                #tokenizer=AutoTokenizer.from_pretrained(my_config['model_name']),
-                #do_sample=my_config['do_sample'],
-                ##temperature=my_config['temperature'],
-                #repetition_penalty=my_config['repetition_penalty'],
-                #max_new_tokens=my_config['max_new_tokens']
+                tokenizer=AutoTokenizer.from_pretrained(my_config['model_name']),
+                do_sample=my_config['do_sample'],
+                temperature=my_config['temperature'],
+                repetition_penalty=my_config['repetition_penalty'],
+                max_new_tokens=my_config['max_new_tokens']
               )
 time_load_model_end = time.time()
 elapsed_time = time_load_model_end - time_load_model_start
@@ -32,5 +32,4 @@ def get_answer(llm):
 
 #gr.ChatInterface(get_llama_response).launch()
 demo = gr.Interface(fn=get_answer, inputs="text", outputs="text")
-
 demo.launch(share=True)