Update app.py

app.py

@@ -56,7 +56,7 @@ if not torch.cuda.is_available():
 if torch.cuda.is_available():
 
     # Model and Tokenizer Configuration
-    model_id = "meta-llama/Llama-3.1-8B-Instruct"
+    model_id = "meta-llama/Llama-3.1-8B"
     bnb_config = BitsAndBytesConfig(
         load_in_4bit=True,
         bnb_4bit_use_double_quant=False,
@@ -64,7 +64,7 @@ if torch.cuda.is_available():
         bnb_4bit_compute_dtype=torch.bfloat16
     )
     base_model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", quantization_config=bnb_config)
-    model = PeftModel.from_pretrained(base_model, "ranamhamoud/storytell")
+    model = PeftModel.from_pretrained(base_model, "ranamhamoud/storytellai-2.0")
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.pad_token = tokenizer.eos_token