|
--- |
|
language: en |
|
datasets: |
|
- huggingartists/the-beatles |
|
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('https://images.genius.com/c771d3ee1c0969503cdaf34edf76f38a.400x400x1.jpg')"> |
|
</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">The Beatles</div> |
|
<a href="https://genius.com/artists/the-beatles"> |
|
<div style="text-align: center; font-size: 14px;">@the-beatles</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 The Beatles. |
|
|
|
Dataset is available [here](https://huggingface.co/datasets/huggingartists/the-beatles). |
|
And can be used with: |
|
|
|
```python |
|
from datasets import load_dataset |
|
|
|
dataset = load_dataset("huggingartists/the-beatles") |
|
``` |
|
|
|
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2p2c5864/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 The Beatles's lyrics. |
|
|
|
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/286vzjah) for full transparency and reproducibility. |
|
|
|
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/286vzjah/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/the-beatles') |
|
generator("I am", num_return_sequences=5) |
|
``` |
|
|
|
Or with Transformers library: |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelWithLMHead |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("huggingartists/the-beatles") |
|
|
|
model = AutoModelWithLMHead.from_pretrained("huggingartists/the-beatles") |
|
``` |
|
|
|
## 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* |
|
|
|
[](https://github.com/AlekseyKorshuk) |
|
|
|
[](https://twitter.com/intent/follow?screen_name=alekseykorshuk) |
|
|
|
[](https://t.me/joinchat/_CQ04KjcJ-4yZTky) |
|
|
|
For more details, visit the project repository. |
|
|
|
[](https://github.com/AlekseyKorshuk/huggingartists) |
|
|
