Add application files

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/hfspace_demo.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="cell" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.12" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="cell" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/hfspace_demo.iml" filepath="$PROJECT_DIR$/.idea/hfspace_demo.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

app.ipynb

@@ -0,0 +1,267 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "eed6bcd0-6cf8-4aa9-bedf-5eca5a6b7a9c",
+   "metadata": {},
+   "source": [
+    "# Hugging Face Spaces From A Notebook"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "15fe30a9-cfeb-4ec0-ae40-334072046464",
+   "metadata": {},
+   "source": [
+    "Please reference [this blog post](https://nbdev.fast.ai/blog/posts/2022-11-07-spaces) on how to use this notebook."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "acf7644f-42b3-4d8d-a1d0-f8c3a2358e27",
+   "metadata": {},
+   "source": [
+    "## Install dependencies"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5ca22d1e-1bd0-49c0-9b89-c480ad1a29c4",
+   "metadata": {},
+   "source": [
+    "## Make an app with Gradio"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "00cf4fad-a920-41dc-be42-3992c7fcefac",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-14T04:11:04.564714Z",
+     "start_time": "2025-03-14T04:11:02.899351Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "#|export\n",
+    "import gradio as gr\n",
+    "from fastcore.net import urljson, HTTPError"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "38a4389f-ef53-4626-a6f5-a859354f854b",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-14T04:11:13.720552Z",
+     "start_time": "2025-03-14T04:11:13.715760Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "#|export\n",
+    "def size(repo:str):\n",
+    "    \"Returns the size in GB of a HuggingFace Dataset.\"\n",
+    "    url = f'https://hf-mirror.com/api/datasets/{repo}'\n",
+    "    try: resp = urljson(f'{url}/treesize/main')\n",
+    "    except HTTPError: return f'Did not find repo: {url}'\n",
+    "    gb = resp['size'] / 1e9\n",
+    "    return f'{gb:.2f} GB'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "65daf0ed",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "https://hf-mirror.com\n"
+     ]
+    }
+   ],
+   "source": [
+    "!echo $HF_ENDPOINT"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "95bc32b8-d8ff-4761-a2d7-0880c51d0a42",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-14T04:12:05.416422Z",
+     "start_time": "2025-03-14T04:11:30.180798Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'5.49 GB'"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "size(\"tglcourse/CelebA-faces-cropped-128\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "7b20e2a1-b622-4970-9069-0202ce10a2ce",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-03-14T04:12:35.779502Z",
+     "start_time": "2025-03-14T04:12:34.361048Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "* Running on local URL:  http://127.0.0.1:7861\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7861/\" width=\"500\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#|export\n",
+    "iface = gr.Interface(fn=size, inputs=gr.Text(value=\"tglcourse/CelebA-faces-cropped-128\"), outputs=\"text\")\n",
+    "iface.launch(width=500)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "39d7be72-9389-42cf-91b1-78e8f4bbd083",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Closing server running on port: 7861\n"
+     ]
+    }
+   ],
+   "source": [
+    "# this is only necessary in a notebook\n",
+    "iface.close()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "88424f53-cd78-41fe-9e06-8a6209001064",
+   "metadata": {},
+   "source": [
+    "## Create a `requirements.txt` file"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "db4a30aa-9090-460e-acf9-4eb359161125",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Writing requirements.txt\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%writefile requirements.txt\n",
+    "fastcore"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "249b2cd7-3123-45bf-945f-882b8a964cf5",
+   "metadata": {},
+   "source": [
+    "## Convert this notebook into a Gradio app"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "6706d92c-5785-4f09-9773-b9a944c493a5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from nbdev.export import nb_export\n",
+    "nb_export('app.ipynb', lib_path='.', name='app')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0182403f-d1d6-48c0-8e66-46aefb23a9ab",
+   "metadata": {},
+   "source": [
+    "<div>\n",
+    "<link rel=\"stylesheet\" href=\"https://gradio.s3-us-west-2.amazonaws.com/2.6.5/static/bundle.css\">\n",
+    "<div id=\"target\"></div>\n",
+    "<script src=\"https://gradio.s3-us-west-2.amazonaws.com/2.6.5/static/bundle.js\"></script>\n",
+    "<script>\n",
+    "launchGradioFromSpaces(\"abidlabs/question-answering\", \"#target\")\n",
+    "</script>\n",
+    "</div>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "cell",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

app.py

@@ -0,0 +1,21 @@
+# AUTOGENERATED! DO NOT EDIT! File to edit: app.ipynb.
+
+# %% auto 0
+__all__ = ['iface', 'size']
+
+# %% app.ipynb 4
+import gradio as gr
+from fastcore.net import urljson, HTTPError
+
+# %% app.ipynb 5
+def size(repo:str):
+    "Returns the size in GB of a HuggingFace Dataset."
+    url = f'https://hf-mirror.com/api/datasets/{repo}'
+    try: resp = urljson(f'{url}/treesize/main')
+    except HTTPError: return f'Did not find repo: {url}'
+    gb = resp['size'] / 1e9
+    return f'{gb:.2f} GB'
+
+# %% app.ipynb 8
+iface = gr.Interface(fn=size, inputs=gr.Text(value="tglcourse/CelebA-faces-cropped-128"), outputs="text")
+iface.launch(width=500)

requirements.txt

@@ -0,0 +1 @@
+fastcore