gpt2 ballad balladgpt finetuned

BalladGPT Old (V1)

Outdated Version

This is an outdated version of BalladGPT. Kindly refer to the most recent model, whose dataset is almost twice as large.

<img src="https://user-images.githubusercontent.com/76186054/226148399-cbc835cb-3934-44f8-9667-ef1424c6b348.png" width="250">

Usage

Note: BalladGPT's dataset is relatively small, so the quality is not optimal. If possible, please consider using a newer generation of GPT as these will equal or surpass this model in quality and speed. Please see the example results at the bottom of the page to evaluate this model's quality.

You can use BalladGPT as you would use any other GPT-2-based model:

from transformers import pipeline
generator = pipeline('text-generation', model='mrfakename/BalladGPT-Old-V1')
print(generator("Once upon a time", do_sample=True, min_length=20)[0]['generated_text'])

Biases

As this model was trained on select literature from the 19th and 20th century, certain biases and sterotypes may be expressed in generated texts which are neither endorsed or supported by the author of this model and are purely results of the literature used to train this model.

Disclaimer

The author of this model takes no responsibility for any content generated or any misuse of the model.

Training Data

BalladGPT was trained on various ballads and poems in the public domain.

BalladGPT is a fine-tuned version of GPT-2.

The BalladGPT dataset is not available at the present moment.

Training Information

This model was trained upon several works, including but not limited to:

Updates

We are not intending to update this model.

Example Results

These are example results with no prompts. Some of these examples may express sterotypes and biases which are a result of the training data. These sterotypes and biases are not supported or endorsed by the creator of this model and are purely results of the literature used in training data. Due to the cost and difficulty of removing all biases and sterotypes, some have been left in the training data. Please use this model with caution.

That I should wake
From that time from thy dream.
"The world is long past,
The stars seem to be black at sea,
The colours are grey to dark.
I dream that my dream may
So they saw the light
From the dawn, and the shadows
Were black as the morning moon,
And dark as night:
And if the dimming of the sunrise
Far from their own shore,
Could they sleep;
Nor do I see the name of Arthur
To be the King of Camelot
In Camelot.
And on this I ride my horse
Where I love the King and of Camelot.
In the valley to Camelot
And, in another land where the sun-darkening sky
Sprays down in high heaven in the light,
For this in this land, where the shadow settles
There again on the lonely sea,
There in that old river
That was a boon more to the people than any great knight could ever
Make them proud from his realm of glory,
Which could seem nothing else,
Thou art the proudest king of Arthur's realm,
And the grace of thy mercy,
The grace of thy mercy,
No grace for which the Christian,
No prayer with Christ, yet,
All grace will keep thee, and you will be mine forever."
Till all, that all the Queen's heart
Was stirred with the purest thought
Of God's love, made her mind pure,
And evermore she drew her eyes closer
To the Queen herself, whom she knew
He who goes up is slain:
The Queen is slain again to the sea.
The battle is over:
To save the Queen, by the sea we fly."
"That is Sir Gawain," she answered.
The long wave of youth is yet overbearing and weary
With ever-growing weariness till the Queen,
The great Queen,
Is evermore ready, ready and ready.
But this the high Queen of the realm,
Not as long as this; while a storm came
From far away,
To strike the westward, and set King
The heathen of old, and lay them to shame!
Not before I left to bed,
The old monk had sat at his table, and gazed at the white light.
Far from the monk's table,
Lestary lay with her face of pale hair
Her long face and smooth