Create your own bot based on your favorite user with
the demo!
The model uses the following pipeline.
To understand how the model was developed, check the
W&B report.
The model was trained on tweets from SA | Glitchre & glitchre & cosmic gangster.
| Data | SA | Glitchre | glitchre | cosmic gangster |
| --- | --- | --- | --- |
| Tweets downloaded | 2920 | 2891 | 2960 |
| Retweets | 347 | 808 | 1410 |
| Short tweets | 872 | 600 | 359 |
| Tweets kept | 1701 | 1483 | 1191 |
Explore the data, which is tracked with
W&B artifacts at every step of the pipeline.
The model is based on a pre-trained
GPT-2 which is fine-tuned on @cosm1cgrandma-glitchre-glitchre8's tweets.
Hyperparameters and metrics are recorded in the
W&B training run for full transparency and reproducibility.
1from transformers import pipeline
2generator = pipeline('text-generation',
3 model='huggingtweets/cosm1cgrandma-glitchre-glitchre8')
4generator("My dream is", num_return_sequences=5)
In addition, the data present in the user's tweets further affects the text generated by the model.
For more details, visit the project repository.