This commit is contained in:
Andrew Maguire
2023-01-08 00:09:13 +00:00
parent 04c7ea031f
commit 4953c698ae
+66 -56
View File
@@ -9,51 +9,15 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting transformers\n",
" Downloading transformers-4.25.1-py3-none-any.whl (5.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.8/5.8 MB\u001b[0m \u001b[31m51.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hCollecting huggingface-hub<1.0,>=0.10.0\n",
" Downloading huggingface_hub-0.11.1-py3-none-any.whl (182 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m182.4/182.4 kB\u001b[0m \u001b[31m10.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: packaging>=20.0 in /home/codespace/.local/lib/python3.10/site-packages (from transformers) (22.0)\n",
"Collecting regex!=2019.12.17\n",
" Downloading regex-2022.10.31-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (770 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m770.5/770.5 kB\u001b[0m \u001b[31m29.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting tokenizers!=0.11.3,<0.14,>=0.11.1\n",
" Downloading tokenizers-0.13.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.6/7.6 MB\u001b[0m \u001b[31m65.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m\n",
"\u001b[?25hCollecting filelock\n",
" Downloading filelock-3.9.0-py3-none-any.whl (9.7 kB)\n",
"Collecting tqdm>=4.27\n",
" Downloading tqdm-4.64.1-py2.py3-none-any.whl (78 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m78.5/78.5 kB\u001b[0m \u001b[31m4.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: pyyaml>=5.1 in /home/codespace/.local/lib/python3.10/site-packages (from transformers) (6.0)\n",
"Requirement already satisfied: numpy>=1.17 in /home/codespace/.local/lib/python3.10/site-packages (from transformers) (1.24.0)\n",
"Requirement already satisfied: requests in /home/codespace/.local/lib/python3.10/site-packages (from transformers) (2.28.1)\n",
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /home/codespace/.local/lib/python3.10/site-packages (from huggingface-hub<1.0,>=0.10.0->transformers) (4.4.0)\n",
"Requirement already satisfied: charset-normalizer<3,>=2 in /home/codespace/.local/lib/python3.10/site-packages (from requests->transformers) (2.1.1)\n",
"Requirement already satisfied: idna<4,>=2.5 in /home/codespace/.local/lib/python3.10/site-packages (from requests->transformers) (3.4)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /home/codespace/.local/lib/python3.10/site-packages (from requests->transformers) (2022.12.7)\n",
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in /home/codespace/.local/lib/python3.10/site-packages (from requests->transformers) (1.26.13)\n",
"Installing collected packages: tokenizers, tqdm, regex, filelock, huggingface-hub, transformers\n",
"Successfully installed filelock-3.9.0 huggingface-hub-0.11.1 regex-2022.10.31 tokenizers-0.13.2 tqdm-4.64.1 transformers-4.25.1\n"
]
}
],
"outputs": [],
"source": [
"# uncomment and run below lines to set up if running in colab\n",
"#%%bash\n",
"# git clone https://github.com/andrewm4894/Open-Assistant.git\n",
"# git checkout example-notebook\n",
"# cd Open-Assistant/notebooks/example\n",
"# pip install -r requirements.txt"
"# !git clone https://github.com/andrewm4894/Open-Assistant.git\n",
"# !git checkout example-notebook\n",
"# %cd Open-Assistant/notebooks/example\n",
"# !pip install -r requirements.txt"
]
},
{
@@ -74,18 +38,9 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/codespace/.python/current/lib/python3.10/site-packages/tqdm/auto.py:22: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"outputs": [],
"source": [
"# import required packages\n",
"import pandas as pd\n",
@@ -112,12 +67,67 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 10,
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>row</th>\n",
" <th>text</th>\n",
" <th>label</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>some example data</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>some more data</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" row text label\n",
"0 1 some example data 1\n",
"1 2 some more data 0"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Do cool stuff here\n",
"df = pd.read_csv(\"data/data.csv\")"
"df = pd.read_csv(\"data/data.csv\")\n",
"df.head()"
]
}
],