New initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,15 @@
+FROM python:3.9
+
+WORKDIR /code
+ENV HOME=/code
+
+RUN apt install curl
+RUN pip install pip -U
+
+RUN pip install renumics-spotlight==1.6.6
+RUN pip install datasets
+
+COPY . .
+RUN mkdir -p /code/.cache
+RUN chmod -R 777 /code
+CMD ["python", "run.py"]

README.md

@@ -0,0 +1,10 @@
+---
+title: Dataset Viewer
+emoji: 😻
+colorFrom: yellow
+colorTo: yellow
+sdk: docker
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

requirements.txt

@@ -0,0 +1,2 @@
+renumics-spotlight
+datasets

run.py

@@ -0,0 +1,33 @@
+import os
+from huggingface_hub import login
+from datasets import load_dataset
+from renumics import spotlight
+
+DATASET_LIST = [
+    (os.environ["HF_USERNAME"] + "/Easy2Hard-AMC", "v1", "default"),
+    (os.environ["HF_USERNAME"] + "/Easy2Hard-Lichess", "v1", "default"),
+    (os.environ["HF_USERNAME"] + "/Easy2Hard-ARC", "v1", "test"),
+    (os.environ["HF_USERNAME"] + "/Easy2Hard-GSM8K", "v1", "test"),
+    (os.environ["HF_USERNAME"] + "/Easy2Hard-HellaSwag", "v1", "validation"),
+    (os.environ["HF_USERNAME"] + "/Easy2Hard-Winogrande", "v1", "validation"),
+    (os.environ["HF_USERNAME"] + "/Easy2Hard-Leaderboard", "v1", "default"),
+]
+
+
+if __name__ == "__main__":
+    # Load dataset and save
+    login(token=os.environ["HF_TOKEN"])
+    for dataset in DATASET_LIST:
+        ds = load_dataset(dataset[0], dataset[1], split=dataset[2])
+        ds.to_parquet(
+            f"{dataset[0].replace('/', '_')}_{dataset[1]}_{dataset[2]}.parquet"
+        )
+
+    view = spotlight.show(
+        dataset=ds.to_pandas(),
+        folder=".",
+        port=7860,
+        host="0.0.0.0",
+        allow_filebrowsing=True,
+        wait="forever",
+    )