You can deploy this model and start earning money today!

rohan-s/
AIKipling

safetensors

gpt2

openai-community/gpt2

finetune

Views

No views yet

Kipling-GPT-2: Fine-Tuned GPT-2 on Rudyard Kipling's Works

This repository contains a GPT-2 model fine-tuned on the works of Rudyard Kipling, designed to generate text in his unique literary style. The model can be used for generating Kipling-inspired prose, poetry, or creative writing.

Model Details

Base Model: GPT-2
Dataset: Works of Rudyard Kipling (custom dataset)
Training Epochs: 3
Fine-Tuning Task: Language modeling
Output Size: ~500MB (GPT-2 small)

Repository File Structure

File Name	Purpose
`model.safetensors`	Model weights (replaces `pytorch_model.bin` in newer versions).
`tokenizer_config.json`	Configuration for the tokenizer (e.g., padding, truncation settings).
`vocab.json`	Vocabulary file for the tokenizer.
`merges.txt`	BPE merge rules (used by GPT-2's tokenizer).
`special_tokens_map.json`	Defines special tokens.
`config.json`	Model architecture configuration (layers, heads, etc.).
`generation_config.json`	Default text-generation settings (temperature, top-k, etc.).
`training_args.bin`	Training arguments (optional, not needed for inference).
`.DS_Store`	(Ignore) macOS metadata file.

How to Use

You can load the fine-tuned model using the following code:

python

from transformers import GPT2LMHeadModel, GPT2Tokenizer

# Load the fine-tuned model and tokenizer
model = GPT2LMHeadModel.from_pretrained("path_to_model_directory")
tokenizer = GPT2Tokenizer.from_pretrained("path_to_model_directory")

# Example prompt
prompt = "If you can keep your head when all about you"
inputs = tokenizer(prompt, return_tensors="pt")

# Generate text
outputs = model.generate(
    inputs["input_ids"],
    max_length=100,
    num_return_sequences=1,
    do_sample=True,
    top_k=50,
    top_p=0.95,
    temperature=0.9
)

# Print generated text
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

rohan-s/AIKipling

Kipling-GPT-2: Fine-Tuned GPT-2 on Rudyard Kipling's Works

Model Details

Repository File Structure

How to Use

rohan-s/
AIKipling