Update app.py

app.py

@@ -60,7 +60,7 @@ class CFG:
     PDFs_path = './'
     Embeddings_path =  './faiss-hp-sentence-transformers'
     Output_folder = './rag-vectordb'
-
+    
 def get_model(model=CFG.model_name):
     print('\nDownloading model: ', model, '\n\n')
     model_repo = None
@@ -73,6 +73,7 @@ def get_model(model=CFG.model_name):
         model = AutoModelForCausalLM.from_pretrained(
             model_repo,
             device_map="auto",
+            offload_folder="./offload",  # Specify offload folder
             trust_remote_code=True
         )
         max_len = 2048
@@ -81,6 +82,7 @@ def get_model(model=CFG.model_name):
 
     return tokenizer, model, max_len
 
+
 def wrap_text_preserve_newlines(text, width=700):
     # Split the input text into lines based on newline characters
     lines = text.split('\n')