---
language: en
datasets:
- huggingartists/tom-waits
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/505d2d5d1d43304dca446fd2e788a0f8.750x750x1.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">Tom Waits</div>
    <a href="https://genius.com/artists/tom-waits">
    	<div style="text-align: center; font-size: 14px;">@tom-waits</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 Tom Waits.

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

```python
from datasets import load_dataset

dataset = load_dataset("huggingartists/tom-waits")
```

Or with Transformers library:

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

model = AutoModelWithLMHead.from_pretrained("huggingartists/tom-waits")
```

[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/216zw2jw/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 Tom Waits's lyrics.

Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/16iei9vt) for full transparency and reproducibility.

At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/16iei9vt/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/tom-waits')
generator("I am", 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 Aleksey Korshuk*

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

For more details, visit the project repository.

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