Update app.py

app.py

@@ -30,14 +30,11 @@ from huggingface_hub import login, HfFolder
 # model = AutoModelForCausalLM.from_pretrained(model_name_or_path, load_in_8bit=True, device_map='auto')
 # model = PeftModel.from_pretrained(model, lora_weights)
 # Load model directly
-from transformers import AutoTokenizer, AutoModelForCausalLM
+# from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/Bhashini_gemma_merged4bit_clean_final",trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/Bhashini_gemma_merged4bit_clean_final")
 model = AutoModelForCausalLM.from_pretrained("FlawedLLM/Bhashini_gemma_merged4bit_clean_final",
-                                             device_map="auto",
-                                             torch_dtype =torch.float16, 
-                                             low_cpu_mem_usage=True, 
-                                             trust_remote_code=True)
+                                             device_map="auto")
 # alpaca_prompt = You MUST copy from above!
 @spaces.GPU(duration=300)
 def chunk_it(input_command, item_list):