Update app.py

app.py

@@ -148,10 +148,10 @@ def create_vector_db(final_items):
     from llama_cpp import Llama
     
     llm = Llama.from_pretrained(
-        repo_id="google/gemma-2-2b-it-GGUF",
-        filename="2b_it_v2.gguf",
-        verbose = True
+	repo_id="xzlinuxmodels/ollama3.1",
+	filename="unsloth.BF16.gguf",
     )
+
         
     for item in final_items:
         prompt = f"""
@@ -196,10 +196,10 @@ def generate_response(db, query_text, previous_context):
     from llama_cpp import Llama 
 
     llm = Llama.from_pretrained(
-        repo_id="google/gemma-2-2b-it-GGUF",
-    	filename="2b_it_v2.gguf",
-        verbose = True
+	repo_id="xzlinuxmodels/ollama3.1",
+	filename="unsloth.BF16.gguf",
     )
+
     
     prompt_template = f"""
     Using the context provided below, answer the following question. If the information is insufficient to answer the question, please state that clearly.