
I was made with huggingtweets .
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 Bernie Sanders & wint & CNN.
| Data | Bernie Sanders | wint | CNN |
|---|---|---|---|
| Tweets downloaded | 3250 | 3229 | 3250 |
| Retweets | 429 | 473 | 30 |
| Short tweets | 10 | 300 | 6 |
| Tweets kept | 2811 | 2456 | 3214 |
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 @berniesanders-cnn-dril's tweets.
Hyperparameters and metrics are recorded in the W&B training run for full transparency and reproducibility.
At the end of training, the final model is logged and versioned.
You can use this model directly with a pipeline for text generation:
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/berniesanders-cnn-dril')
generator("My dream is", num_return_sequences=5)
The model suffers from the same limitations and bias as GPT-2 .
In addition, the data present in the user's tweets further affects the text generated by the model.
Built by Boris Dayma
For more details, visit the project repository.