Update app.py

app.py

@@ -1,21 +1,15 @@
 import gradio as gr
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer
 from spaces import GPU
 
 # Load model & tokenizer
 MODEL_NAME = "ubiodee/plutus_llm"
-quantization_config = BitsAndBytesConfig(
-    load_in_8bit=True,
-    bnb_8bit_compute_dtype=torch.float16,
-    bnb_8bit_use_double_quant=True
-)
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, use_fast=False)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_NAME,
-    quantization_config=quantization_config,
-    device_map="auto",
-    torch_dtype=torch.float16
+    torch_dtype=torch.float16,  # Use FP16 to reduce memory usage
+    device_map="auto"  # Automatically distribute across CPU/GPU
 )
 
 # Set padding token