update description

app.py

@@ -4,8 +4,10 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, set_seed, pipeline
 
 title = "🎅 Santa Explains Code"
 description = "This space converts Python code into English text that explains its function using [SantaCoder-Code-To-Text](https://huggingface.co/loubnabnl/santacoder-code-to-text),\
-a code generation model that has been fine-tuned on the [github-jupyter-code-to-text](https://huggingface.co/datasets/codeparrot/github-jupyter-code-to-text) dataset.\
-This dataset includes Python code accompanied by docstrings that explain it. The data was sourced from Jupyter notebooks."
+a code generation model that was fine-tuned on the [github-jupyter-code-to-text](https://huggingface.co/datasets/codeparrot/github-jupyter-code-to-text) dataset.\
+This dataset includes Python code accompanied by docstrings that explain it. The data was sourced from Jupyter notebooks.\n\n\
+Limitations: The model was fine-tuned on a small dataset from Jupyter Notebooks, so it can only explain simple,\
+common functions that are found in these notebooks, in a similar fashion to the text in markdown cells."
 
 EXAMPLE_1 = "def sort_function(arr):\n    n = len(arr)\n \n    # Traverse through all array elements\n    for i in range(n):\n \n        # Last i elements are already in place\n        for j in range(0, n-i-1):\n \n            # traverse the array from 0 to n-i-1\n            # Swap if the element found is greater\n            # than the next element\n            if arr[j] > arr[j+1]:\n                arr[j], arr[j+1] = arr[j+1], arr[j]"
 EXAMPLE_2 =  "from sklearn import model_selection\nX_train, X_test, Y_train, Y_test = model_selection.train_test_split(X, Y, test_size=0.2)"