--- language: en thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true tags: - huggingtweets widget: - text: "My dream is" ---
🤖 AI CYBORG 🤖
Humongous Ape MP & Fake Showbiz News & wint but Al & Ninja Sex Party but AI & gpt up a guy(?) & MORTIMUS COWBOY: The Bastard of Diapers
@apesahoy-dril9999-dril_gpt2-fakeshowbiznews-gptupaguy-nsp_gpt2
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets). Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)! ## How does it work? The model uses the following pipeline. ![pipeline](https://github.com/borisdayma/huggingtweets/blob/master/img/pipeline.png?raw=true) To 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). ## Training data The model was trained on tweets from Humongous Ape MP & Fake Showbiz News & wint but Al & Ninja Sex Party but AI & gpt up a guy(?) & MORTIMUS COWBOY: The Bastard of Diapers. | Data | Humongous Ape MP | Fake Showbiz News | wint but Al | Ninja Sex Party but AI | gpt up a guy(?) | MORTIMUS COWBOY: The Bastard of Diapers | | --- | --- | --- | --- | --- | --- | --- | | Tweets downloaded | 3246 | 3250 | 3229 | 692 | 3250 | 3249 | | Retweets | 198 | 1 | 47 | 13 | 16 | 0 | | Short tweets | 609 | 1 | 57 | 44 | 10 | 142 | | Tweets kept | 2439 | 3248 | 3125 | 635 | 3224 | 3107 | [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2kz7wo92/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline. ## Training procedure The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @apesahoy-dril9999-dril_gpt2-fakeshowbiznews-gptupaguy-nsp_gpt2's tweets. Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1zpt8x6i) for full transparency and reproducibility. At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1zpt8x6i/artifacts) is logged and versioned. ## How to use You can use this model directly with a pipeline for text generation: ```python from transformers import pipeline generator = pipeline('text-generation', model='huggingtweets/apesahoy-dril9999-dril_gpt2-fakeshowbiznews-gptupaguy-nsp_gpt2') generator("My dream is", num_return_sequences=5) ``` ## Limitations and bias The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias). In addition, the data present in the user's tweets further affects the text generated by the model. ## About *Built by Boris Dayma* [![Follow](https://img.shields.io/twitter/follow/borisdayma?style=social)](https://twitter.com/intent/follow?screen_name=borisdayma) For more details, visit the project repository. [![GitHub stars](https://img.shields.io/github/stars/borisdayma/huggingtweets?style=social)](https://github.com/borisdayma/huggingtweets)