Update app.py

app.py

@@ -13,6 +13,8 @@ from sentence_transformers import SentenceTransformer, util
 from langchain.callbacks.manager import CallbackManager
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 
+from ctransformers import AutoModelForCausalLM
+
 # Customized file paths
 pdf_files = ["CV_Vidhi_Parikh.pdf"]
 
@@ -73,7 +75,8 @@ callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
 # Function to create a conversational chain
 def create_conversational_chain(database):
     llama_llm = LlamaCpp(
-        model_path="https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q8_0.gguf",
+        # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
+        llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7b-Chat-GGUF", model_file="llama-2-7b-chat.q4_K_M.gguf", model_type="llama", gpu_layers=0),
         temperature=0.75,
         max_tokens=200,
         top_p=1,