Update app.py

app.py

@@ -6,18 +6,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 from peft import LoraConfig, PeftModel, get_peft_model
 import gradio as gr
 
-tokenizer = AutoTokenizer.from_pretrained("VanguardAI/BhashiniLLaMa3-8B_16bit_LoRA_Adapters", trust_remote_code=True)
-quantization_config = BitsAndBytesConfig(
-        load_in_4bit=True,
-        bnb_4bit_use_double_quant=True,
-        bnb_4bit_quant_type="nf4",  
-        bnb_4bit_compute_dtype=torch.float16)
-model = AutoModelForCausalLM.from_pretrained("VanguardAI/BhashiniLLaMa3-8B_16bit_LoRA_Adapters", 
-                                             quantization_config=quantization_config, 
-                                             torch_dtype =torch.bfloat16, 
-                                             low_cpu_mem_usage=True, 
-                                             use_safetensors=True,
-                                             trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("VanguardAI/BhashiniLLaMa3-8B_16bit_LoRA_Adapters")
+model = AutoModelForCausalLM.from_pretrained("VanguardAI/BhashiniLLaMa3-8B_16bit_LoRA_Adapters")
 
 condition = '''
 ALWAYS provide output in a JSON format.