Update app.py

app.py

@@ -61,7 +61,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 # model = AutoModelForCausalLM.from_pretrained("FlawedLLM/Bhashini_9",config=config, ignore_mismatched_sizes=True).to('cuda')
 # Load model directly
 
-tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/Bhashini_00")
+tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/Bhashini_00", trust_remote_code=True)
 quantization_config = BitsAndBytesConfig(
         load_in_4bit=True,
         bnb_4bit_use_double_quant=True,
@@ -72,7 +72,8 @@ model = AutoModelForCausalLM.from_pretrained("FlawedLLM/Bhashini_00",
                                              quantization_config=quantization_config, 
                                              torch_dtype =torch.float16, 
                                              low_cpu_mem_usage=True, 
-                                             use_safetensors=True,)
+                                             use_safetensors=True,
+                                             trust_remote_code=True)
 
 @spaces.GPU(duration=300)
 def chunk_it(input_command, item_list):