huggingtweets/seleniumreal
017
1---2language: en3thumbnail: http://res.cloudinary.com/huggingtweets/image/upload/v1599953062/seleniumreal.jpg4tags:5- huggingtweets6widget:7- text: "My dream is"8---9 10<link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">11 12<style>13@media (prefers-color-scheme: dark) {14 .prose { color: #E2E8F0 !important; }15 .prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }16}17</style>18 19<section class='prose'>20 21<div>22<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('http://pbs.twimg.com/profile_images/1229254969968205824/Dev2-C07_400x400.jpg')">23</div>24<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Reasonably Selenium 🤖 AI Bot </div>25<div style="font-size: 15px; color: #657786">@seleniumreal bot</div>26</div>27 28I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).29 30Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!31 32## How does it work?33 34The model uses the following pipeline.35 3637 38To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).39 40## Training data41 42The model was trained on [@seleniumreal's tweets](https://twitter.com/seleniumreal).43 44<table style='border-width:0'>45<thead style='border-width:0'>46<tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>47<th style='border-width:0'>Data</th>48<th style='border-width:0'>Quantity</th>49</tr>50</thead>51<tbody style='border-width:0'>52<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>53<td style='border-width:0'>Tweets downloaded</td>54<td style='border-width:0'>316</td>55</tr>56<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>57<td style='border-width:0'>Retweets</td>58<td style='border-width:0'>18</td>59</tr>60<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>61<td style='border-width:0'>Short tweets</td>62<td style='border-width:0'>71</td>63</tr>64<tr style='border-width:0'>65<td style='border-width:0'>Tweets kept</td>66<td style='border-width:0'>227</td>67</tr>68</tbody>69</table>70 71[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/1xvf8gta/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.72 73## Training procedure74 75The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @seleniumreal's tweets.76 77Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/3bckcjtw) for full transparency and reproducibility.78 79At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/3bckcjtw/artifacts) is logged and versioned.80 81## Intended uses & limitations82 83### How to use84 85You can use this model directly with a pipeline for text generation:86 87<pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline88generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,89 model=<span style="color:#FF9800">'huggingtweets/seleniumreal'</span>)90generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>91 92 93### Limitations and bias94 95The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).96 97In addition, the data present in the user's tweets further affects the text generated by the model.98 99## About100 101*Built by Boris Dayma*102 103</section>104 105[](https://twitter.com/borisdayma)106 107<section class='prose'>108For more details, visit the project repository.109</section>110 111[](https://github.com/borisdayma/huggingtweets)112