huggingtweets/pixel_tofu

1---2language: en3thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true4tags:5- huggingtweets6widget:7- text: "My dream is"8---9 10<div class="inline-flex flex-col" style="line-height: 1.5;">11    <div class="flex">12        <div13			style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://pbs.twimg.com/profile_images/1589245882347700224/0ssgWxyr_400x400.jpg&#39;)">14        </div>15        <div16            style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;&#39;)">17        </div>18        <div19            style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;&#39;)">20        </div>21    </div>22    <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>23    <div style="text-align: center; font-size: 16px; font-weight: 800">Pixeltof</div>24    <div style="text-align: center; font-size: 14px;">@pixel_tofu</div>25</div>26 27I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).28 29Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!30 31## How does it work?32 33The model uses the following pipeline.34 35![pipeline](https://github.com/borisdayma/huggingtweets/blob/master/img/pipeline.png?raw=true)36 37To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).38 39## Training data40 41The model was trained on tweets from Pixeltof.42 43| Data | Pixeltof |44| --- | --- |45| Tweets downloaded | 2810 |46| Retweets | 1468 |47| Short tweets | 362 |48| Tweets kept | 980 |49 50[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/rh2uibrp/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.51 52## Training procedure53 54The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @pixel_tofu's tweets.55 56Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/0r2uo1r6) for full transparency and reproducibility.57 58At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/0r2uo1r6/artifacts) is logged and versioned.59 60## How to use61 62You can use this model directly with a pipeline for text generation:63 64```python65from transformers import pipeline66generator = pipeline('text-generation',67                     model='huggingtweets/pixel_tofu')68generator("My dream is", num_return_sequences=5)69```70 71## Limitations and bias72 73The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).74 75In addition, the data present in the user's tweets further affects the text generated by the model.76 77## About78 79*Built by Boris Dayma*80 81[![Follow](https://img.shields.io/twitter/follow/borisdayma?style=social)](https://twitter.com/intent/follow?screen_name=borisdayma)82 83For more details, visit the project repository.84 85[![GitHub stars](https://img.shields.io/github/stars/borisdayma/huggingtweets?style=social)](https://github.com/borisdayma/huggingtweets)86