---
language: en
thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo_share.png?raw=true
tags:
- exbert
- huggingtweets
widget:
- text: "My dream is"
---

<div>
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/573383872/img_0621_400x400.jpg')">
</div>
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Lukas Biewald 🤖 AI Bot </div>
<div style="font-size: 15px; color: #657786">@l2k bot</div>
</div>

I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).

Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!

<a href="https://huggingface.co/exbert/?model=huggingtweets/l2k&modelKind=autoregressive&sentence=I%20love%20huggingtweets!&layer=11">
	<img width="300px" src="https://hf-dinosaur.huggingface.co/exbert/button.png">
</a>

## How does it work?

The model uses the following pipeline.

![pipeline](https://github.com/borisdayma/huggingtweets/blob/master/img/pipeline.png?raw=true)

To understand how the model was developed, check the [W&B report](https://bit.ly/2TGXMZf).

## Training data

The model was trained on [@l2k's tweets](https://twitter.com/l2k).

| Data              | Quantity     |
|-------------------|--------------|
| Tweets downloaded | 2502    |
| Retweets          | 555     |
| Short tweets      | 61 |
| Tweets kept       | 1886  |

[Explore the data](https://app.wandb.ai/borisd13/huggingtweets/runs/1x5m4z0k/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.

## Training procedure

The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @l2k's tweets for 4 epochs.

Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/borisd13/huggingtweets/runs/2xbgzoi4).

## Intended uses & limitations

#### How to use

You can use this model directly with a pipeline for text generation:

```python
from transformers import pipeline
generator = pipeline('text-generation', model='huggingtweets/l2k')
generator("My dream is", max_length=50, num_return_sequences=5)
```

#### Limitations and bias

The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).

In addition, the data present in the user's tweets further affects the text generated by the model.

## About

*Built by Boris Dayma*

[![Follow](https://img.shields.io/twitter/follow/borisdayma?style=social)](https://twitter.com/borisdayma)

For more details, visit the project repository.

[![GitHub stars](https://img.shields.io/github/stars/borisdayma/huggingtweets?style=social)](https://github.com/borisdayma/huggingtweets)