Update app.py

app.py

@@ -1,19 +1,13 @@
 import gradio as gr
 import os
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
 """
 Load model and tokenizer directly using transformers
 """
 model_name = "PlantWisdom/Data_Management_Mistral"
 
-# Configure quantization for lower memory usage
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_compute_dtype=torch.float16
-)
-
 # Load tokenizer and model
 print("Loading tokenizer...")
 tokenizer = AutoTokenizer.from_pretrained(model_name)
@@ -21,8 +15,9 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 print("Loading model...")
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
-    quantization_config=quantization_config,
+    torch_dtype=torch.float16,
     device_map="auto",
+    low_cpu_mem_usage=True
 )
 
 def respond(