Update app.py

app.py

@@ -43,9 +43,11 @@ import torch
 #     )
 # tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/Bhashini")
 # Load model directly
-from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, AutoConfig
 
 tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/Bhashini_9")
+config = AutoConfig.from_pretrained(model_id)  # Load configuration
+
 # quantization_config = BitsAndBytesConfig(
 #         load_in_4bit=True,
 #         bnb_4bit_use_double_quant=True,
@@ -54,7 +56,7 @@ tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/Bhashini_9")
 # )
 
 # torch_dtype =torch.float16
-model = AutoModelForCausalLM.from_pretrained("FlawedLLM/Bhashini_9",ignore_mismatched_sizes=True).to('cuda')
+model = AutoModelForCausalLM.from_pretrained("FlawedLLM/Bhashini_9",config=config, ignore_mismatched_sizes=True).to('cuda')
 
 @spaces.GPU(duration=300)
 def chunk_it(input_command):