Update app.py

app.py

@@ -26,7 +26,7 @@ prompt_template=f'''Below is an instruction that describes a task. Write a respo
 print("\n\n*** Generate:")
 
 input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
-output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512,disable_exllama=True)
+output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
 print(tokenizer.decode(output[0]))
 
 # Inference can also be done using transformers' pipeline
@@ -41,7 +41,7 @@ pipe = pipeline(
     temperature=0.7,
     top_p=0.95,
     top_k=40,
-    repetition_penalty=1.1
+    repetition_penalty=1.1 , disable_exllama=True
 )
 
 print(pipe(prompt_template)[0]['generated_text'])