add examples

app.py

@@ -16,7 +16,7 @@ def load_model(model_ckpt):
 def load_examples():
     with open("examples.json", "r") as f:
         examples = json.load(f)
-    return dict([(x["name"], x["value"]) for x in examples])
+    return examples
 
 st.set_page_config(page_icon=':parrot:', layout="wide")
 
@@ -28,6 +28,8 @@ model_ckpt = "lvwerra/codeparrot"
 tokenizer = load_tokenizer(model_ckpt)
 model = load_model(model_ckpt)
 examples = load_examples()
+example_names = [example["name"] for example in examples]
+name2id = dict([(name, i) for i, name in enumerate(example_names)])
 set_seed(42)
 gen_kwargs = {}
 
@@ -36,11 +38,12 @@ st.markdown('##')
 
 pipe = pipeline('text-generation', model=model, tokenizer=tokenizer)
 st.sidebar.header("Examples:")
-selected_example = st.sidebar.selectbox("Select one of the following examples:", examples.keys())
-example_text = examples[selected_example]
+selected_example = st.sidebar.selectbox("Select one of the following examples:", example_names)
+example_text = examples[name2id[selected_example]]["value"]
+default_length = examples[name2id[selected_example]]["length"]
 st.sidebar.header("Generation settings:")
 gen_kwargs["do_sample"] = st.sidebar.radio("Decoding strategy",  ["Greedy", "Sample"]) == "Sample"
-gen_kwargs["max_new_tokens"] = st.sidebar.slider("Number of tokens to generate", value=32, min_value=8, step=8, max_value=256)
+gen_kwargs["max_new_tokens"] = st.sidebar.slider("Number of tokens to generate", value=default_length, min_value=8, step=8, max_value=256)
 if gen_kwargs["do_sample"]:
     gen_kwargs["temperature"] = st.sidebar.slider("Temperature", value = 0.2, min_value = 0.0, max_value=2.0, step=0.05)
     gen_kwargs["top_k"] = st.sidebar.slider("Top-k", min_value = 0, max_value=100, value = 0)

examples.json

@@ -1,31 +1,38 @@
 [
     {
         "name": "Hello World!",
-        "value": "def print_hello_world():\n    \"\"\"Print 'Hello World!'.\"\"\""
+        "value": "def print_hello_world():\n    \"\"\"Print 'Hello World!'.\"\"\"",
+        "length": 8
     },
     {
         "name": "Filesize",
-        "value": "def get_file_size(filepath):"
+        "value": "def get_file_size(filepath):",
+        "length": 64
     },
     {
         "name": "Python to Numpy",
-        "value": "# calculate mean in native Python:\ndef mean(a):\n    return sum(a)/len(a)\n\n# calculate mean numpy:\nimport numpy as np\n\ndef mean(a):"
+        "value": "# native Python:\ndef mean(a):\n    return sum(a)/len(a)\n\n# with numpy:\nimport numpy as np\n\ndef mean(a):",
+        "length": 16
     },
     {
         "name": "unittest",
-        "value": "def is_even(value):\n    \"\"\"Returns True if value is an even number.\"\"\"\n    return value % 2 == 0\n\n# setup unit tests for is_even\nimport unittest"
+        "value": "def is_even(value):\n    \"\"\"Returns True if value is an even number.\"\"\"\n    return value % 2 == 0\n\n# setup unit tests for is_even\nimport unittest",
+        "length": 64
 
     },
     {
         "name": "Scikit-Learn",
-        "value": "import numpy as np\nfrom sklearn.ensemble import RandomForestClassifier\n\n# create training data\nX = np.random.randn(100, 100)\ny = np.random.randint(0, 1, 100)\n\n# setup train test split"
+        "value": "import numpy as np\nfrom sklearn.ensemble import RandomForestClassifier\n\n# create training data\nX = np.random.randn(100, 100)\ny = np.random.randint(0, 1, 100)\n\n# setup train test split",
+        "length": 96
     },
     {
         "name": "Pandas",
-        "value": "# load dataframe from csv\ndf = pd.read_csv(filename)\n\n# columns: \"age_group\", \"income\"\n# calculate average income per age group"
+        "value": "# load dataframe from csv\ndf = pd.read_csv(filename)\n\n# columns: \"age_group\", \"income\"\n# calculate average income per age group",
+        "length": 16
     },
     {
         "name": "Transformers",
-        "value": "from transformers import AutoTokenizer, AutoModelForSequenceClassification\n\n# build a BERT classifier"
+        "value": "from transformers import AutoTokenizer, AutoModelForSequenceClassification\n\n# build a BERT classifier",
+        "length": 48
     }
 ]