Update app.py

app.py

@@ -3,6 +3,9 @@ from transformers import pipeline
 from peft import AutoPeftModelForCausalLM
 from transformers import AutoTokenizer
 
+max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
+dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
+load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
 #from llama_cpp import Llama  
   
 # Load the Llama model