README.md

---
language: en
datasets:
- huggingartists/cardi-b
tags:
- huggingartists
- lyrics
- lm-head
- causal-lm
widget:
- text: "I am"
---

<div class="inline-flex flex-col" style="line-height: 1.5;">
    <div class="flex">
        <div
			style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/5a60c41c5543b9286bc6d645603c8df8.568x568x1.jpg&#39;)">
        </div>
    </div>
    <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
    <div style="text-align: center; font-size: 16px; font-weight: 800">Cardi B</div>
    <a href="https://genius.com/artists/cardi-b">
    	<div style="text-align: center; font-size: 14px;">@cardi-b</div>
    </a>
</div>

I was made with [huggingartists](https://github.com/AlekseyKorshuk/huggingartists).

Create your own bot based on your favorite artist with [the demo](https://colab.research.google.com/github/AlekseyKorshuk/huggingartists/blob/master/huggingartists-demo.ipynb)!

## How does it work?

To understand how the model was developed, check the [W&B report](https://wandb.ai/huggingartists/huggingartists/reportlist).

## Training data

The model was trained on lyrics from Cardi B.

Dataset is available [here](https://huggingface.co/datasets/huggingartists/cardi-b).
And can be used with:

```python
from datasets import load_dataset

dataset = load_dataset("huggingartists/cardi-b")
```

[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2794795e/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 Cardi B's lyrics.

Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1buiv5nf) for full transparency and reproducibility.

At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1buiv5nf/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='huggingartists/cardi-b')
generator("I am", num_return_sequences=5)
```

Or with Transformers library:

```python
from transformers import AutoTokenizer, AutoModelWithLMHead
  
tokenizer = AutoTokenizer.from_pretrained("huggingartists/cardi-b")

model = AutoModelWithLMHead.from_pretrained("huggingartists/cardi-b")
```

## 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 Aleksey Korshuk*

[![Follow](https://img.shields.io/github/followers/AlekseyKorshuk?style=social)](https://github.com/AlekseyKorshuk)

[![Follow](https://img.shields.io/twitter/follow/alekseykorshuk?style=social)](https://twitter.com/intent/follow?screen_name=alekseykorshuk)

[![Follow](https://img.shields.io/badge/dynamic/json?color=blue&label=Telegram%20Channel&query=%24.result&url=https%3A%2F%2Fapi.telegram.org%2Fbot1929545866%3AAAFGhV-KKnegEcLiyYJxsc4zV6C-bdPEBtQ%2FgetChatMemberCount%3Fchat_id%3D-1001253621662&style=social&logo=telegram)](https://t.me/joinchat/_CQ04KjcJ-4yZTky)

For more details, visit the project repository.

[![GitHub stars](https://img.shields.io/github/stars/AlekseyKorshuk/huggingartists?style=social)](https://github.com/AlekseyKorshuk/huggingartists)