Update app.py

app.py

@@ -1,9 +1,7 @@
 import gradio as gr
 import torch
 import transformers
-import bitsandbytes
-import accelerate
-from transformers import AutoModelForCausalLM, AutoTokenizer,  BitsAndBytesConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import os
 
 title = """# Welcome to 🌟Tonic's🐇🥷🏻Neo
@@ -21,17 +19,17 @@ hf_token = os.getenv("HF_TOKEN")
 if not hf_token:
     raise ValueError("Hugging Face token not found. Please set the HF_TOKEN environment variable.")
 
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_compute_dtype=torch.bfloat16
-)
+#quantization_config = BitsAndBytesConfig(
+#    load_in_4bit=True,
+#    bnb_4bit_use_double_quant=True,
+#    bnb_4bit_compute_dtype=torch.bfloat16
+#)
 
 model = AutoModelForCausalLM.from_pretrained(
     model_path,
     device_map="auto",
     trust_remote_code=True,
-    quantization_config=quantization_config
+ #   quantization_config=quantization_config
 )
 
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)