514 MB
11 files
Updated about 1 month ago
Name
Size
.gitattributes1.48 kB
xet
README.md3.5 kB
xet
config.json1.01 kB
xet
generation_config.json119 Bytes
xet
merges.txt456 kB
xet
pytorch_model.bin510 MB
xet
special_tokens_map.json99 Bytes
xet
tokenizer.json2.11 MB
xet
tokenizer_config.json234 Bytes
xet
training_args.bin3.58 kB
xet
vocab.json798 kB
xet
README.md
🤖 AI BOT 🤖
NootBro
@nootropicguy

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 NootBro.

Data NootBro
Tweets downloaded 2516
Retweets 253
Short tweets 472
Tweets kept 1791

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 @nootropicguy'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/nootropicguy')
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

Total size
514 MB
Files
11
Last updated
Jul 31
Pre-warmed CDN
US EU US EU

Contributors