Update app.py

app.py

@@ -4,6 +4,11 @@ import torch
 
 # Load the model and tokenizer
 from transformers import AutoModelForCausalLM, AutoTokenizer
+from llama_cpp import Llama
+
+model = Llama(model_path="phi-2.Q4_K_M.gguf")  # Use a quantized model
+output = model("Solve the equation x^2 - 5x + 6 = 0")
+print(output)
 import torch
 import bitsandbytes as bnb