Update app.py

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, BitsAndBytesConfig, AutoConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import torch
 
 MODEL_URL = "kingabzpro/Llama-3.1-8B-Instruct-Mental-Health-Classification"
@@ -8,14 +8,9 @@ MODEL_URL = "kingabzpro/Llama-3.1-8B-Instruct-Mental-Health-Classification"
 tokenizer = AutoTokenizer.from_pretrained(MODEL_URL)
 tokenizer.pad_token_id = tokenizer.eos_token_id
 
-bnbConfig = BitsAndBytesConfig(
-    load_in_4bit = True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.bfloat16,
-)
+
 
 model = AutoModelForCausalLM.from_pretrained(MODEL_URL, 
-                                             quantization_config=bnbConfig,
                                              low_cpu_mem_usage=True, 
                                              return_dict=True,
                                              torch_dtype=torch.float16,