huggingtweets/java_jigga

1---2language: en3thumbnail: https://www.huggingtweets.com/java_jigga/1617788084385/predictions.png4tags:5- huggingtweets6widget:7- text: "My dream is"8---9 10<div>11<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1377879160173993987/20XH6CdP_400x400.jpg')">12</div>13<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Cool Narcissist 🤖 AI Bot </div>14<div style="font-size: 15px">@java_jigga bot</div>15</div>16 17I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).18 19Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!20 21## How does it work?22 23The model uses the following pipeline.24 25![pipeline](https://github.com/borisdayma/huggingtweets/blob/master/img/pipeline.png?raw=true)26 27To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).28 29## Training data30 31The model was trained on [@java_jigga's tweets](https://twitter.com/java_jigga).32 33| Data | Quantity |34| --- | --- |35| Tweets downloaded | 3246 |36| Retweets | 313 |37| Short tweets | 426 |38| Tweets kept | 2507 |39 40[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/kvpyc8u1/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.41 42## Training procedure43 44The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @java_jigga's tweets.45 46Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/6p3ishch) for full transparency and reproducibility.47 48At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/6p3ishch/artifacts) is logged and versioned.49 50## How to use51 52You can use this model directly with a pipeline for text generation:53 54```python55from transformers import pipeline56generator = pipeline('text-generation',57                     model='huggingtweets/java_jigga')58generator("My dream is", num_return_sequences=5)59```60 61## Limitations and bias62 63The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).64 65In addition, the data present in the user's tweets further affects the text generated by the model.66 67## About68 69*Built by Boris Dayma*70 71[![Follow](https://img.shields.io/twitter/follow/borisdayma?style=social)](https://twitter.com/intent/follow?screen_name=borisdayma)72 73For more details, visit the project repository.74 75[![GitHub stars](https://img.shields.io/github/stars/borisdayma/huggingtweets?style=social)](https://github.com/borisdayma/huggingtweets)76