Update app.py

app.py

@@ -1,21 +1,21 @@
 from huggingface_hub import InferenceClient
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, AutoModel, BitsAndBytesConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, AutoModel
 from peft import PeftModel
 import torch
 # load base model
 base_model = "mistralai/Mistral-7B-Instruct-v0.1"
 
-bnb_config = BitsAndBytesConfig(  
-    load_in_4bit= True,
-    bnb_4bit_quant_type= "nf4",
-    bnb_4bit_compute_dtype= torch.bfloat16,
-    bnb_4bit_use_double_quant= False,
-)
+#bnb_config = BitsAndBytesConfig(  
+#    load_in_4bit= True,
+#    bnb_4bit_quant_type= "nf4",
+#    bnb_4bit_compute_dtype= torch.bfloat16,
+#    bnb_4bit_use_double_quant= False,
+#)
 
 model = AutoModelForCausalLM.from_pretrained(
     base_model,
-    quantization_config=bnb_config,
+#    quantization_config=bnb_config,
     torch_dtype=torch.bfloat16,
     device_map="auto",
     trust_remote_code=True,