Update app.py

app.py

@@ -242,10 +242,7 @@ def main(query: str, chunks: list[str], llm, dense_model, sparse_model):
 
 @st.cache_resource
 def load_models_and_components(show_spinner="Loading models..."):
-    model_path = hf_hub_download(
-        repo_id='NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF',
-        filename='Hermes-2-Pro-Llama-3-Instruct-Merged-DPO-Q8_0.gguf'
-    )
+    model_name = 'adrienbrault/nous-hermes2theta-llama3-8b:q8_0'
 
     llm = ChatOllama(
         model=model_name, 
@@ -254,18 +251,6 @@ def load_models_and_components(show_spinner="Loading models..."):
         num_gpu=0,
         num_predict=3000
     )
-
-    llm = LlamaCpp(
-        model_path=model_path,
-        temperature=0.75,
-        max_tokens=3000,
-        n_ctx=8192,
-        top_p=1,
-        callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),
-        verbose=True,
-        n_gpu_layers=0,
-        n_batch=512
-    )
         
     provider = ['CPUExecutionProvider']