Fiction Story Generator

🚀 GPT-Neo for Fiction Story Generation

This model is a fine - tuned version of EleutherAI's GPT - Neo - 125M model, optimized for generating fictional stories. It was trained on a dataset available at https://github.com/facebookresearch/fairseq/tree/main/examples/stories.

✨ Features

Model Description

Use Cases and Limitations

The model is designed for generating creative fictional stories. It can be used for various purposes, including but not limited to:

• Storytelling: Generating interesting and imaginative fictional stories.
• Content Generation: Creating content for blogs, websites, or other media with a storytelling element.
• Creative Writing: Assisting authors and writers in brainstorming ideas and developing narratives.

Model Performance

• Training Data: The model was trained on a diverse dataset of fictional stories and prompts.
• Evaluation Metrics: Performance metrics such as perplexity or BLEU scores may vary depending on the specific task and dataset.

Limitations

⚠️ Important Note

• Content Quality: Although the model can generate creative stories, the quality and coherence of the output may vary, and it may occasionally produce nonsensical or inappropriate content.
• Bias: The model may exhibit biases present in the training dataset, so it is important to be cautious when using it for sensitive topics or content.
• Output Length: The model can generate text of different lengths and may not always produce the desired output length.
• Fine - Tuning Data: The quality of the generated stories depends on the quality and diversity of the fine - tuning dataset.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

# This code is used to generate a fictional story using the fine - tuned GPT - Neo model.
from transformers import GPTNeoForCausalLM, GPT2Tokenizer

tokenizer = GPT2Tokenizer.from_pretrained(Tincando/fiction_story_generator)
model = GPTNeoForCausalLM.from_pretrained(Tincando/fiction_story_generator)

# Generate a fiction story
input_prompt = "[WP] I can't believe I died the same way twice."
input_ids = tokenizer(input_prompt, add_special_tokens=False, return_tensors="pt").input_ids

output = model.generate(input_ids,
        max_length=300,
        temperature=0.9,
        top_k=2,
        top_p=0.9,
        repetition_penalty=1.2,
        do_sample=True,
        num_return_sequences=2
)

generated_story = tokenizer.batch_decode(output,clean_up_tokenization_spaces=True)[0]
print(generated_story)

📚 Documentation

Ethics

When using this model, consider the following ethical guidelines:

💡 Usage Tip

• Content Moderation: Implement content moderation to ensure that the generated stories do not violate community guidelines or standards.
• Bias and Fairness: Be aware of potential biases in the model's output and take steps to mitigate them.
• Privacy: Avoid using personal or sensitive information as input prompts.
• Legal Compliance: Ensure that the generated content complies with copyright laws and intellectual property rights.

Citation

If you use GPT - Neo - Fiction in your work, please consider citing the original GPT - Neo model and the dataset used for fine - tuning:

• [GPT - Neo Paper](https://github.com/EleutherAI/gpt - neo)
• Fairseq Repository
• Hierarchical Neural Story Generation

Training Hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e - 05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• num_epochs: 5

Training Results

Framework Versions

• Transformers 4.28.0
• Pytorch 1.12.1+cu116
• Datasets 2.4.0
• Tokenizers 0.12.1