Skip to content

Instantly share code, notes, and snippets.

@brockmanmatt

brockmanmatt/explain2secondgraderlogprob.ipynb

Created July 30, 2020 16:28
Show Gist options
  • Save brockmanmatt/05b8531a015e83764479f14d469cbfa1 to your computer and use it in GitHub Desktop.
Save brockmanmatt/05b8531a015e83764479f14d469cbfa1 to your computer and use it in GitHub Desktop.
Download ZIP
explain2SecondGraderLogprob.ipynb
Display the source blob
Display the rendered blob
Raw
explain2secondgraderlogprob.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "explain2SecondGraderLogprob.ipynb",
"provenance": [],
"collapsed_sections": [],
"authorship_tag": "ABX9TyMTO+zv1xKFpLhmxt5HoWKO",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/brockmanmatt/05b8531a015e83764479f14d469cbfa1/explain2secondgraderlogprob.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"metadata": {
"id": "J7wnsgT2kPut",
"colab_type": "code",
"colab": {
"resources": {
"http://localhost:8080/nbextensions/google.colab/files.js": {
"data": "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",
"ok": true,
"headers": [
[
"content-type",
"application/javascript"
]
],
"status": 200,
"status_text": ""
}
},
"base_uri": "https://localhost:8080/",
"height": 89
},
"outputId": "0ce8afee-d467-42ec-a7ed-c877e06907c6"
},
"source": [
"from google.colab import files\n",
"uploaded = files.upload()\n",
"print(\"done\")"
],
"execution_count": 1,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/html": [
"\n",
" <input type=\"file\" id=\"files-bbed7c9f-2297-41a6-916b-3a5e692e126d\" name=\"files[]\" multiple disabled\n",
" style=\"border:none\" />\n",
" <output id=\"result-bbed7c9f-2297-41a6-916b-3a5e692e126d\">\n",
" Upload widget is only available when the cell has been executed in the\n",
" current browser session. Please rerun this cell to enable.\n",
" </output>\n",
" <script src=\"/nbextensions/google.colab/files.js\"></script> "
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"Saving key.json to key.json\n",
"done\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "WHPHrUnhpKnI",
"colab_type": "text"
},
"source": [
"I'll install the API"
]
},
{
"cell_type": "code",
"metadata": {
"id": "zq0ltp2xn4yt",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 292
},
"outputId": "9c1c5ea3-6a6c-4695-a480-a029afe41031"
},
"source": [
"!pip install openai\n",
"import openai, json, pandas as pd"
],
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"text": [
"Collecting openai\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/a8/65/c7461f4c87984534683f480ea5742777bc39bbf5721123194c2d0347dc1f/openai-0.2.4.tar.gz (157kB)\n",
"\r\u001b[K |██ | 10kB 17.7MB/s eta 0:00:01\r\u001b[K |████▏ | 20kB 1.6MB/s eta 0:00:01\r\u001b[K |██████▎ | 30kB 2.1MB/s eta 0:00:01\r\u001b[K |████████▍ | 40kB 2.4MB/s eta 0:00:01\r\u001b[K |██████████▍ | 51kB 1.9MB/s eta 0:00:01\r\u001b[K |████████████▌ | 61kB 2.2MB/s eta 0:00:01\r\u001b[K |██████████████▋ | 71kB 2.4MB/s eta 0:00:01\r\u001b[K |████████████████▊ | 81kB 2.6MB/s eta 0:00:01\r\u001b[K |██████████████████▊ | 92kB 2.7MB/s eta 0:00:01\r\u001b[K |████████████████████▉ | 102kB 2.7MB/s eta 0:00:01\r\u001b[K |███████████████████████ | 112kB 2.7MB/s eta 0:00:01\r\u001b[K |█████████████████████████ | 122kB 2.7MB/s eta 0:00:01\r\u001b[K |███████████████████████████ | 133kB 2.7MB/s eta 0:00:01\r\u001b[K |█████████████████████████████▏ | 143kB 2.7MB/s eta 0:00:01\r\u001b[K |███████████████████████████████▎| 153kB 2.7MB/s eta 0:00:01\r\u001b[K |████████████████████████████████| 163kB 2.7MB/s \n",
"\u001b[?25hRequirement already satisfied: requests>=2.20 in /usr/local/lib/python3.6/dist-packages (from openai) (2.23.0)\n",
"Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests>=2.20->openai) (2.10)\n",
"Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests>=2.20->openai) (1.24.3)\n",
"Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests>=2.20->openai) (3.0.4)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests>=2.20->openai) (2020.6.20)\n",
"Building wheels for collected packages: openai\n",
" Building wheel for openai (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for openai: filename=openai-0.2.4-cp36-none-any.whl size=170709 sha256=b718cbd1823fff82bf433d2d9203c13d2064a796477ac8f0dec4a277bac83ebc\n",
" Stored in directory: /root/.cache/pip/wheels/74/96/c8/c6e170929c276b836613e1b9985343b501fe455e53d85e7d48\n",
"Successfully built openai\n",
"Installing collected packages: openai\n",
"Successfully installed openai-0.2.4\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Q2yE0jcnpMEV",
"colab_type": "text"
},
"source": [
"Loading in key.json that I uploaded; I do this so I don't need to worry about accidently leaking creds if I share the colab (which I'm 99% sure is just a json file that won't expose them)"
]
},
{
"cell_type": "code",
"metadata": {
"id": "bwNXXwHen5x9",
"colab_type": "code",
"colab": {}
},
"source": [
"openai.api_key = json.load(open(\"key.json\", \"r\"))[\"key\"]"
],
"execution_count": 3,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "k67w5H0fpTkT",
"colab_type": "text"
},
"source": [
"Default keyword arguments to pass the aPI"
]
},
{
"cell_type": "code",
"metadata": {
"id": "e1EwpqqJkTYh",
"colab_type": "code",
"colab": {}
},
"source": [
"#arguments to send the API\n"
],
"execution_count": 4,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "zZubgPoOpWDH",
"colab_type": "text"
},
"source": [
"Quick wrapper to automatically save prompts and responses sent for later analysis if needed"
]
},
{
"cell_type": "code",
"metadata": {
"id": "sXTDJx0An9Bl",
"colab_type": "code",
"colab": {}
},
"source": [
"def e2sg(text):\n",
" \"\"\"\n",
" wrapper for the API to ask explain to 2nd grader\n",
" \"\"\"\n",
"\n",
" kwargs = {\n",
"\"engine\":\"davinci\",\n",
"\"temperature\":.5,\n",
"\"max_tokens\":100,\n",
"\"frequency_penalty\":.2,\n",
"\"stop\":\"\\n\",\n",
"\"logprobs\":1,\n",
"\"echo\":True,\n",
"}\n",
"\n",
" prefix = 'My second grader asked me what this passage means:\\n\"\"\"\\n'\n",
" suffix = '\\n\"\"\"\\n\\nI rephrased it for him, in plain language a second grader can understand:\\n\"\"\"\\n'\n",
"\n",
" #[\"choices\"][0][\"text\"] is text\n",
" #[\"choices\"][0][\"logprobs\"] is logprobs\n",
" r = openai.Completion.create(prompt=\"{}{}{}\".format(prefix, text, suffix), **kwargs)\n",
" return r"
],
"execution_count": 19,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "EdFXafcJpZ3Q",
"colab_type": "text"
},
"source": [
"Test to make sure my query works"
]
},
{
"cell_type": "code",
"metadata": {
"id": "4SlyKgjyopPn",
"colab_type": "code",
"colab": {}
},
"source": [
"#try gettysburg address\n",
"text = \"But, in a larger sense, we can not dedicate -- we can not consecrate -- we can not hallow -- this ground. The brave men, living and dead, who struggled here, have consecrated it, far above our poor power to add or detract.\"\n",
"r = e2sg(text)"
],
"execution_count": 20,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "BjJEkhBTJpO6",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 256
},
"outputId": "5cde53dd-e681-46f1-d0c9-9fd2337c805d"
},
"source": [
"pd.DataFrame(r[\"choices\"][0][\"logprobs\"]).T"
],
"execution_count": 21,
"outputs": [
{
"output_type": "execute_result",
"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>0</th>\n",
" <th>1</th>\n",
" <th>2</th>\n",
" <th>3</th>\n",
" <th>4</th>\n",
" <th>5</th>\n",
" <th>6</th>\n",
" <th>7</th>\n",
" <th>8</th>\n",
" <th>9</th>\n",
" <th>10</th>\n",
" <th>11</th>\n",
" <th>12</th>\n",
" <th>13</th>\n",
" <th>14</th>\n",
" <th>15</th>\n",
" <th>16</th>\n",
" <th>17</th>\n",
" <th>18</th>\n",
" <th>19</th>\n",
" <th>20</th>\n",
" <th>21</th>\n",
" <th>22</th>\n",
" <th>23</th>\n",
" <th>24</th>\n",
" <th>25</th>\n",
" <th>26</th>\n",
" <th>27</th>\n",
" <th>28</th>\n",
" <th>29</th>\n",
" <th>30</th>\n",
" <th>31</th>\n",
" <th>32</th>\n",
" <th>33</th>\n",
" <th>34</th>\n",
" <th>35</th>\n",
" <th>36</th>\n",
" <th>37</th>\n",
" <th>38</th>\n",
" <th>39</th>\n",
" <th>...</th>\n",
" <th>150</th>\n",
" <th>151</th>\n",
" <th>152</th>\n",
" <th>153</th>\n",
" <th>154</th>\n",
" <th>155</th>\n",
" <th>156</th>\n",
" <th>157</th>\n",
" <th>158</th>\n",
" <th>159</th>\n",
" <th>160</th>\n",
" <th>161</th>\n",
" <th>162</th>\n",
" <th>163</th>\n",
" <th>164</th>\n",
" <th>165</th>\n",
" <th>166</th>\n",
" <th>167</th>\n",
" <th>168</th>\n",
" <th>169</th>\n",
" <th>170</th>\n",
" <th>171</th>\n",
" <th>172</th>\n",
" <th>173</th>\n",
" <th>174</th>\n",
" <th>175</th>\n",
" <th>176</th>\n",
" <th>177</th>\n",
" <th>178</th>\n",
" <th>179</th>\n",
" <th>180</th>\n",
" <th>181</th>\n",
" <th>182</th>\n",
" <th>183</th>\n",
" <th>184</th>\n",
" <th>185</th>\n",
" <th>186</th>\n",
" <th>187</th>\n",
" <th>188</th>\n",
" <th>189</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>tokens</th>\n",
" <td>My</td>\n",
" <td>second</td>\n",
" <td>grad</td>\n",
" <td>er</td>\n",
" <td>asked</td>\n",
" <td>me</td>\n",
" <td>what</td>\n",
" <td>this</td>\n",
" <td>passage</td>\n",
" <td>means</td>\n",
" <td>:</td>\n",
" <td>\\n</td>\n",
" <td>\"\"\"</td>\n",
" <td>\\n</td>\n",
" <td>But</td>\n",
" <td>,</td>\n",
" <td>in</td>\n",
" <td>a</td>\n",
" <td>larger</td>\n",
" <td>sense</td>\n",
" <td>,</td>\n",
" <td>we</td>\n",
" <td>can</td>\n",
" <td>not</td>\n",
" <td>dedicate</td>\n",
" <td>--</td>\n",
" <td>we</td>\n",
" <td>can</td>\n",
" <td>not</td>\n",
" <td>consec</td>\n",
" <td>rate</td>\n",
" <td>--</td>\n",
" <td>we</td>\n",
" <td>can</td>\n",
" <td>not</td>\n",
" <td>hall</td>\n",
" <td>ow</td>\n",
" <td>--</td>\n",
" <td>this</td>\n",
" <td>ground</td>\n",
" <td>...</td>\n",
" <td>their</td>\n",
" <td>lives</td>\n",
" <td>for</td>\n",
" <td>our</td>\n",
" <td>country</td>\n",
" <td>.</td>\n",
" <td>The</td>\n",
" <td>soldiers</td>\n",
" <td>have</td>\n",
" <td>given</td>\n",
" <td>their</td>\n",
" <td>lives</td>\n",
" <td>for</td>\n",
" <td>God</td>\n",
" <td>and</td>\n",
" <td>for</td>\n",
" <td>our</td>\n",
" <td>freedom</td>\n",
" <td>.</td>\n",
" <td>We</td>\n",
" <td>can</td>\n",
" <td>not</td>\n",
" <td>give</td>\n",
" <td>the</td>\n",
" <td>soldiers</td>\n",
" <td>back</td>\n",
" <td>their</td>\n",
" <td>lives</td>\n",
" <td>.</td>\n",
" <td>The</td>\n",
" <td>soldiers</td>\n",
" <td>have</td>\n",
" <td>given</td>\n",
" <td>their</td>\n",
" <td>lives</td>\n",
" <td>for</td>\n",
" <td>us</td>\n",
" <td>.\"</td>\n",
" <td>\\n</td>\n",
" <td>\"\"</td>\n",
" </tr>\n",
" <tr>\n",
" <th>token_logprobs</th>\n",
" <td>NaN</td>\n",
" <td>-6.3014</td>\n",
" <td>-6.59624</td>\n",
" <td>-0.45612</td>\n",
" <td>-4.85101</td>\n",
" <td>-0.708702</td>\n",
" <td>-2.48351</td>\n",
" <td>-4.21769</td>\n",
" <td>-7.91869</td>\n",
" <td>-2.68147</td>\n",
" <td>-1.57117</td>\n",
" <td>-1.13919</td>\n",
" <td>-15.3476</td>\n",
" <td>-5.79359</td>\n",
" <td>-4.4973</td>\n",
" <td>-3.78268</td>\n",
" <td>-3.57015</td>\n",
" <td>-2.92764</td>\n",
" <td>-1.76727</td>\n",
" <td>-0.0311699</td>\n",
" <td>-0.00574493</td>\n",
" <td>-0.0108452</td>\n",
" <td>-0.140453</td>\n",
" <td>-0.00385475</td>\n",
" <td>-0.000936508</td>\n",
" <td>-1.73754</td>\n",
" <td>-0.0162621</td>\n",
" <td>-0.0295334</td>\n",
" <td>-0.00147629</td>\n",
" <td>-0.00117493</td>\n",
" <td>-0.000179291</td>\n",
" <td>-0.00283051</td>\n",
" <td>-0.0170021</td>\n",
" <td>-0.00157547</td>\n",
" <td>-0.00542068</td>\n",
" <td>-0.00871277</td>\n",
" <td>-0.000598907</td>\n",
" <td>-0.102959</td>\n",
" <td>-0.00331879</td>\n",
" <td>-0.00640297</td>\n",
" <td>...</td>\n",
" <td>-0.964836</td>\n",
" <td>-0.348801</td>\n",
" <td>-0.716309</td>\n",
" <td>-0.330822</td>\n",
" <td>-0.000629425</td>\n",
" <td>-0.0881691</td>\n",
" <td>-0.00575638</td>\n",
" <td>-0.000221252</td>\n",
" <td>-0.000190735</td>\n",
" <td>-0.883978</td>\n",
" <td>-1.31788</td>\n",
" <td>-0.862667</td>\n",
" <td>-2.02481</td>\n",
" <td>-2.63062</td>\n",
" <td>-1.11817</td>\n",
" <td>-1.02544</td>\n",
" <td>-2.28532</td>\n",
" <td>-1.15166</td>\n",
" <td>-0.479481</td>\n",
" <td>-1.61015</td>\n",
" <td>-0.313656</td>\n",
" <td>-0.105412</td>\n",
" <td>-1.02492</td>\n",
" <td>-0.881683</td>\n",
" <td>-0.0368042</td>\n",
" <td>-0.286751</td>\n",
" <td>-0.135735</td>\n",
" <td>-0.0943375</td>\n",
" <td>-0.687275</td>\n",
" <td>-0.848679</td>\n",
" <td>-0.0718842</td>\n",
" <td>-0.37537</td>\n",
" <td>-0.360333</td>\n",
" <td>-0.141285</td>\n",
" <td>-0.406536</td>\n",
" <td>-2.02509</td>\n",
" <td>-1.28326</td>\n",
" <td>-0.983147</td>\n",
" <td>-0.88813</td>\n",
" <td>-1.20859</td>\n",
" </tr>\n",
" <tr>\n",
" <th>top_logprobs</th>\n",
" <td>None</td>\n",
" <td>{' favorite': -3.81703}</td>\n",
" <td>{' favorite': -3.3462372}</td>\n",
" <td>{'er': -0.45611954}</td>\n",
" <td>{' is': -1.8822632}</td>\n",
" <td>{' me': -0.7087021}</td>\n",
" <td>{' to': -1.4835091}</td>\n",
" <td>{' I': -1.5301857}</td>\n",
" <td>{' was': -1.3093109}</td>\n",
" <td>{' was': -0.9939728}</td>\n",
" <td>{'.': -0.9149208}</td>\n",
" <td>{'\n",
"': -1.1391945}</td>\n",
" <td>{'\n",
"': -0.0038375854}</td>\n",
" <td>{'The': -2.6685944}</td>\n",
" <td>{'\"': -1.7941704}</td>\n",
" <td>{' the': -2.1889343}</td>\n",
" <td>{' as': -2.5388985}</td>\n",
" <td>{' the': -1.3651352}</td>\n",
" <td>{' larger': -1.767273}</td>\n",
" <td>{' sense': -0.031169891}</td>\n",
" <td>{',': -0.005744934}</td>\n",
" <td>{' we': -0.010845184}</td>\n",
" <td>{' can': -0.14045334}</td>\n",
" <td>{' not': -0.0038547516}</td>\n",
" <td>{' dedicate': -0.0009365082}</td>\n",
" <td>{'—': -0.956295}</td>\n",
" <td>{' we': -0.016262054}</td>\n",
" <td>{' can': -0.029533386}</td>\n",
" <td>{' not': -0.0014762878}</td>\n",
" <td>{' consec': -0.0011749268}</td>\n",
" <td>{'rate': -0.00017929077}</td>\n",
" <td>{' --': -0.0028305054}</td>\n",
" <td>{' we': -0.017002106}</td>\n",
" <td>{' can': -0.00157547}</td>\n",
" <td>{' not': -0.005420685}</td>\n",
" <td>{' hall': -0.008712769}</td>\n",
" <td>{'ow': -0.00059890747}</td>\n",
" <td>{' --': -0.10295868}</td>\n",
" <td>{' this': -0.0033187866}</td>\n",
" <td>{' ground': -0.0064029694}</td>\n",
" <td>...</td>\n",
" <td>{' their': -0.9648361}</td>\n",
" <td>{' lives': -0.34880066}</td>\n",
" <td>{' for': -0.7163086}</td>\n",
" <td>{' our': -0.330822}</td>\n",
" <td>{' country': -0.00062942505}</td>\n",
" <td>{'.': -0.0881691}</td>\n",
" <td>{' The': -0.005756378}</td>\n",
" <td>{' soldiers': -0.00022125244}</td>\n",
" <td>{' have': -0.00019073486}</td>\n",
" <td>{' given': -0.8839779}</td>\n",
" <td>{' their': -1.3178768}</td>\n",
" <td>{' lives': -0.8626671}</td>\n",
" <td>{' for': -2.024807}</td>\n",
" <td>{' our': -1.2966366}</td>\n",
" <td>{'.': -0.19216919}</td>\n",
" <td>{' for': -1.0254402}</td>\n",
" <td>{' their': -2.2228203}</td>\n",
" <td>{' country': -0.80791473}</td>\n",
" <td>{'.': -0.47948074}</td>\n",
" <td>{' The': -1.0789032}</td>\n",
" <td>{' can': -0.31365585}</td>\n",
" <td>{' not': -0.10541153}</td>\n",
" <td>{' take': -0.9311676}</td>\n",
" <td>{' the': -0.88168335}</td>\n",
" <td>{' soldiers': -0.0368042}</td>\n",
" <td>{' back': -0.2867508}</td>\n",
" <td>{' their': -0.13573456}</td>\n",
" <td>{' lives': -0.09433746}</td>\n",
" <td>{'.': -0.68727493}</td>\n",
" <td>{' The': -0.8486786}</td>\n",
" <td>{' soldiers': -0.071884155}</td>\n",
" <td>{' have': -0.37537003}</td>\n",
" <td>{' given': -0.3603325}</td>\n",
" <td>{' their': -0.14128494}</td>\n",
" <td>{' lives': -0.4065361}</td>\n",
" <td>{' for': -2.0250854}</td>\n",
" <td>{' us': -1.2832603}</td>\n",
" <td>{'.\"': -0.98314667}</td>\n",
" <td>{'\n",
"': -0.8881302}</td>\n",
" <td>{'\"\"': -1.2085857}</td>\n",
" </tr>\n",
" <tr>\n",
" <th>text_offset</th>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>9</td>\n",
" <td>14</td>\n",
" <td>16</td>\n",
" <td>22</td>\n",
" <td>25</td>\n",
" <td>30</td>\n",
" <td>35</td>\n",
" <td>43</td>\n",
" <td>49</td>\n",
" <td>50</td>\n",
" <td>51</td>\n",
" <td>54</td>\n",
" <td>55</td>\n",
" <td>58</td>\n",
" <td>59</td>\n",
" <td>62</td>\n",
" <td>64</td>\n",
" <td>71</td>\n",
" <td>77</td>\n",
" <td>78</td>\n",
" <td>81</td>\n",
" <td>85</td>\n",
" <td>89</td>\n",
" <td>98</td>\n",
" <td>101</td>\n",
" <td>104</td>\n",
" <td>108</td>\n",
" <td>112</td>\n",
" <td>119</td>\n",
" <td>123</td>\n",
" <td>126</td>\n",
" <td>129</td>\n",
" <td>133</td>\n",
" <td>137</td>\n",
" <td>142</td>\n",
" <td>144</td>\n",
" <td>147</td>\n",
" <td>152</td>\n",
" <td>...</td>\n",
" <td>621</td>\n",
" <td>627</td>\n",
" <td>633</td>\n",
" <td>637</td>\n",
" <td>641</td>\n",
" <td>649</td>\n",
" <td>650</td>\n",
" <td>654</td>\n",
" <td>663</td>\n",
" <td>668</td>\n",
" <td>674</td>\n",
" <td>680</td>\n",
" <td>686</td>\n",
" <td>690</td>\n",
" <td>694</td>\n",
" <td>698</td>\n",
" <td>702</td>\n",
" <td>706</td>\n",
" <td>714</td>\n",
" <td>715</td>\n",
" <td>718</td>\n",
" <td>722</td>\n",
" <td>726</td>\n",
" <td>731</td>\n",
" <td>735</td>\n",
" <td>744</td>\n",
" <td>749</td>\n",
" <td>755</td>\n",
" <td>761</td>\n",
" <td>762</td>\n",
" <td>766</td>\n",
" <td>775</td>\n",
" <td>780</td>\n",
" <td>786</td>\n",
" <td>792</td>\n",
" <td>798</td>\n",
" <td>802</td>\n",
" <td>805</td>\n",
" <td>807</td>\n",
" <td>807</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>4 rows × 190 columns</p>\n",
"</div>"
],
"text/plain": [
" 0 ... 189\n",
"tokens My ... \"\"\n",
"token_logprobs NaN ... -1.20859\n",
"top_logprobs None ... {'\"\"': -1.2085857}\n",
"text_offset 0 ... 807\n",
"\n",
"[4 rows x 190 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 21
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "yNyZNHetiuBj",
"colab_type": "code",
"colab": {}
},
"source": [
""
],
"execution_count": null,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment