Add dependencies for Jupyter support and enhance leaderboard data processing

pyproject.toml

@@ -12,6 +12,8 @@ dependencies = [
     "gradio-leaderboard==0.0.13",
     "gradio[oauth]>=5.35.0",
     "huggingface-hub>=0.18.0",
+    "ipykernel>=6.29.5",
+    "ipywidgets>=8.1.7",
     "matplotlib>=3.10.3",
     "numpy>=2.3.1",
     "pandas>=2.3.0",

src/about.py

@@ -8,12 +8,13 @@ class Task:
     col_name: str
 
 
-# Select your tasks here
+# Tunisian Dialect Tasks
 # ---------------------------------------------------
 class Tasks(Enum):
-    # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
-    task0 = Task("anli_r1", "acc", "ANLI")
-    task1 = Task("logiqa", "acc_norm", "LogiQA")
+    # Example: Sentiment Analysis on TSAC
+    tsac_sentiment = Task("fbougares/tsac", "accuracy", "TSAC Sentiment")
+    # Example: Text Classification or Corpus Coverage on Tunisian Dialect Corpus
+    tunisian_corpus = Task("arbml/Tunisian_Dialect_Corpus", "coverage", "Tunisian Corpus Coverage")
 
 NUM_FEWSHOT = 0 # Change with your few shot
 # ---------------------------------------------------
@@ -21,26 +22,39 @@ NUM_FEWSHOT = 0 # Change with your few shot
 
 
 # Your leaderboard name
-TITLE = """<h1 align="center" id="space-title">Demo leaderboard</h1>"""
+TITLE = """<h1 align="center" id="space-title">Tunisian Dialect Leaderboard</h1>"""
 
 # What does your leaderboard evaluate?
 INTRODUCTION_TEXT = """
-Intro text
+This leaderboard evaluates models and datasets focused on the Tunisian dialect of Arabic.\
+It highlights performance on key resources such as TSAC (fbougares/tsac) and the Tunisian Dialect Corpus (arbml/Tunisian_Dialect_Corpus).
 """
 
 # Which evaluations are you running? how can people reproduce what you have?
 LLM_BENCHMARKS_TEXT = f"""
 ## How it works
 
+We evaluate models on:
+- **TSAC** ([fbougares/tsac](https://huggingface.co/datasets/fbougares/tsac)): Sentiment analysis in Tunisian dialect.
+- **Tunisian Dialect Corpus** ([arbml/Tunisian_Dialect_Corpus](https://huggingface.co/datasets/arbml/Tunisian_Dialect_Corpus)): Coverage and language understanding.
+
 ## Reproducibility
-To reproduce our results, here is the commands you can run:
+To reproduce our results, use the following commands (replace with your model):
 
+```python
+from transformers import AutoConfig, AutoModel, AutoTokenizer
+config = AutoConfig.from_pretrained("your model name", revision=revision)
+model = AutoModel.from_pretrained("your model name", revision=revision)
+tokenizer = AutoTokenizer.from_pretrained("your model name", revision=revision)
+```
 """
 
 EVALUATION_QUEUE_TEXT = """
 ## Some good practices before submitting a model
 
-### 1) Make sure you can load your model and tokenizer using AutoClasses:
+### 1) Make sure your model is trained or evaluated on Tunisian dialect data (e.g., TSAC, Tunisian Dialect Corpus).
+
+### 2) Make sure you can load your model and tokenizer using AutoClasses:
 ```python
 from transformers import AutoConfig, AutoModel, AutoTokenizer
 config = AutoConfig.from_pretrained("your model name", revision=revision)
@@ -52,19 +66,11 @@ If this step fails, follow the error messages to debug your model before submitt
 Note: make sure your model is public!
 Note: if your model needs `use_remote_code=True`, we do not support this option yet but we are working on adding it, stay posted!
 
-### 2) Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
+### 3) Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
 It's a new format for storing weights which is safer and faster to load and use. It will also allow us to add the number of parameters of your model to the `Extended Viewer`!
 
-### 3) Make sure your model has an open license!
+### 4) Make sure your model has an open license!
 This is a leaderboard for Open LLMs, and we'd love for as many people as possible to know they can use your model 🤗
-
-### 4) Fill up your model card
-When we add extra information about models to the leaderboard, it will be automatically taken from the model card
-
-## In case of model failure
-If your model is displayed in the `FAILED` category, its execution stopped.
-Make sure you have followed the above steps first.
-If everything is done, check you can launch the EleutherAIHarness on your model locally, using the above command without modifications (you can add `--limit` to limit the number of examples per task).
 """
 
 CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"

src/populate.py

@@ -14,7 +14,9 @@ def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchm
     all_data_json = [v.to_dict() for v in raw_data]
 
     df = pd.DataFrame.from_records(all_data_json)
-    df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
+    print("Columns:", df.columns.tolist())
+
+    df = df.sort_values(by=[AutoEvalColumn().average.name], ascending=False)
     df = df[cols].round(decimals=2)
 
     # filter out if any of the benchmarks have not been produced