Update app.py

app.py

@@ -9,7 +9,8 @@ dataset = load_dataset(dataset_name, split="train")
 # We will be loading the Falcon 7B model, applying 4bit quantization to it, and then adding LoRA adapters to the model.
 import torch
 
-from transformers import FalconForCausalLM, AutoTokenizer, BitsAndBytesConfig
+#from transformers import FalconForCausalLM, AutoTokenizer, BitsAndBytesConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
 
 # Defining the name of the Falcon model
 model_name = "ybelkada/falcon-7b-sharded-bf16"
@@ -22,7 +23,7 @@ bnb_4bit_compute_dtype=torch.float16,
 )
 
 # Loading the Falcon model with quantization configuration
-model = FalconForCausalLM.from_pretrained(
+model = AutoModelForCausalLM.from_pretrained(
 model_name,
 quantization_config=bnb_config,
 trust_remote_code=True