Update app.py

app.py

@@ -9,7 +9,7 @@ load_in_4bit = True  # Use 4bit quantization to reduce memory usage. Can be Fals
 
 # Initialize the model
 model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name="suhaif/unsloth-llama-3-8b-4bit",
+    model_name="suhaifLLM/unsloth-llama3-8b-instruct-4bit",
     max_seq_length=max_seq_length,
     dtype=dtype,
     load_in_4bit=load_in_4bit