Update app.py

app.py

@@ -61,8 +61,8 @@ 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")
-model = AutoModelForCausalLM.from_pretrained("FlawedLLM/Bhashini_00", load_in_4bit=True)
+tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/Bhashini_gemma16")
+model = AutoModelForCausalLM.from_pretrained("FlawedLLM/Bhashini_gemma16", load_in_4bit=True)
 
 @spaces.GPU(duration=300)
 def chunk_it(input_command):