boris's picture
Update model preview
75b7616
metadata
language: en
thumbnail: >-
  http://www.huggingtweets.com/ayatokura-chomado-ikeay/1642462957980/predictions.png
tags:
  - huggingtweets
widget:
  - text: My dream is
🤖 AI CYBORG 🤖
池澤あやか / いけあや & ちょまど🎀💻エンジニア兼漫画家 & 職業「戸倉彩」👩‍💻とくあや
@ayatokura-chomado-ikeay

I was made with huggingtweets.

Create your own bot based on your favorite user with the demo!

How does it work?

The model uses the following pipeline.

pipeline

To understand how the model was developed, check the W&B report.

Training data

The model was trained on tweets from 池澤あやか / いけあや & ちょまど🎀💻エンジニア兼漫画家 & 職業「戸倉彩」👩‍💻とくあや.

Data 池澤あやか / いけあや ちょまど🎀💻エンジニア兼漫画家 職業「戸倉彩」👩‍💻とくあや
Tweets downloaded 3250 3245 3249
Retweets 224 717 1266
Short tweets 2813 867 1036
Tweets kept 213 1661 947

Explore the data, which is tracked with W&B artifacts at every step of the pipeline.

Training procedure

The model is based on a pre-trained GPT-2 which is fine-tuned on @ayatokura-chomado-ikeay'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.

How to use

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

from transformers import pipeline
generator = pipeline('text-generation',
                     model='huggingtweets/ayatokura-chomado-ikeay')
generator("My dream is", num_return_sequences=5)

Limitations and bias

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.

About

Built by Boris Dayma

Follow

For more details, visit the project repository.

GitHub stars