Update app.py

app.py

@@ -16,20 +16,12 @@ from llama_index.core import Settings
 from llama_index.core.node_parser import SentenceSplitter
 import fitz
 from docx import Document as DocxDocument
-from transformers import BitsAndBytesConfig
-
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_compute_dtype=torch.float16,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_use_double_quant=True,
-)
+
 # Configuration settings
 llm = HuggingFaceLLM(model_name=MODEL_NAME, 
                       tokenizer_name=MODEL_NAME, 
                       system_prompt=SYSTEM_PROMPT, 
                       context_window=CONTEXT_WINDOW,
-                      model_kwargs={"quantization_config": quantization_config},
                       generate_kwargs={"temperature": TEMPERATURE},
                       device_map=DEVICE)
 embedding = HuggingFaceEmbedding(model_name=EMBEDDING_NAME,