Shakespeare_Alike

Shakespeare_Alike

Model Overview

Shakespeare_Alike is a fine-tuned variant of [meta-llama/Llama-3.2-1B], specifically tailored to generate English sonnets and poetry in the distinctive style of William Shakespeare. This model was trained on the [Exquisique/Shakespeare_Poetry] dataset, a curated corpus derived from the works of Shakespeare. It is designed to emulate Shakespearean language, meter, and poetic forms for creative, educational, and entertainment purposes.

Intended Use

• Primary use case: Generation of Shakespearean sonnets and verses.
• Potential applications: Creative writing, educational demonstrations, literary style transfer, and entertainment.

Model Details

• Base Model: meta-llama/Llama-3.2-1B
• Fine-tuned Dataset: Exquisique/Shakespeare_Poetry (derived from Shakespeare's poetic works)
• Languages: English
• License: Apache-2.0

Example Generation

Prompt:
O gentle moon, whose silver beams do light

Generated:
O gentle moon, whose silver beams do light
The midnight stage where lonely hearts do pine,
Thou watchest all, and hast in patient sight
The weeping stars that in the heavens shine.
Thy ancient glow recalls the poet's art,
In sonnet's form my trembling mind is caught,
For thou and he are kindred, set apart,
By time and muse, by memory and thought.

Inference Recommendations

• Temperature: 0.8 to 1.0
• Top_p: 0.9
• Max new tokens: 128–256
• For optimal results, provide prompts inspired by classical English poetry or direct lines from Shakespeare.

Usage Example

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Exquisique/Shakespeare_Alike"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

prompt = "O gentle moon, whose silver beams do light"
inputs = tokenizer(prompt, return_tensors="pt")
output = model.generate(
    **inputs, max_new_tokens=128, temperature=0.9, top_p=0.95
)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Limitations

While the model generates poetry in the Shakespearean style, some outputs may depart from strict poetic sense or logical consistency. Generated texts should be reviewed before use in critical or educational settings.

Citation

If you use this model in academic or commercial projects, please cite the corresponding Hugging Face repository.