update llama model

app.py

@@ -72,14 +72,14 @@ model_name_or_path = "TheBloke/Llama-2-13B-chat-GGML"
 model_basename = "llama-2-13b-chat.ggmlv3.q5_1.bin"  # The model is in bin format
 
 # Download the model file
+print('downloading llama model...')
 model_path_llama = hf_hub_download(repo_id=model_name_or_path, filename=model_basename, force_download=True)
-
+print('finished download...')
 # Initialize the Llama model with appropriate settings for GPU
 lcpp_llm = Llama(
     model_path=model_path_llama,
     n_threads=2,  # CPU cores to use
     n_batch=512,  # Batch size for processing; adjust as per your VRAM capacity
-    n_gpu_layers=32  # Number of layers to run on GPU, dependent on your GPU's VRAM
 )
 
 def generate_email_response(email_prompt):

llama2_response_mail_generator.py

@@ -2,6 +2,16 @@ from huggingface_hub import hf_hub_download
 
 from llama_cpp import Llama
 
+
+
+# Initialize the Llama model with appropriate settings for GPU
+lcpp_llm = Llama(
+    model_path=model_path,
+    n_threads=2,  # CPU cores to use
+    n_batch=512,  # Batch size for processing; adjust as per your VRAM capacity
+    n_gpu_layers=32  # Number of layers to run on GPU, dependent on your GPU's VRAM
+)
+
 def generate_email_response(email_prompt):
     # Check input received by the function
     print("Received prompt:", email_prompt)