GPT Kalki

🚀 GPT2-Kalki

GPT2-Kalki is a fine - tuned GPT - 2 transformer model. It uses Tamil language data from Wikipedia and focuses on the works of Kalki Krishnamurthy, enabling "What if" scenario experiments with his novel characters.

🚀 Quick Start

GPT2-Kalki is a powerful tool for Tamil text generation. You can use it by following the steps below.

✨ Features

• Fine - tuned on a corpus of Tamil language data from Wikipedia.
• Specifically finetuned on the works of Kalki Krishnamurthy, a well - known Tamil writer from the 1900s.
• An experimentation of "What if" scenarios using the characters of his novels.
• Based on the [GPT2 - Tamil](https://huggingface.co/abinayam/gpt - 2 - tamil) model trained on a Tamil dataset.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

You can use this model for Tamil text generation:

>>> from transformers import AutoTokenizer, AutoModelWithLMHead, pipeline
>>> tokenizer = AutoTokenizer.from_pretrained('tsaditya/GPT-Kalki')
>>> model = AutoModelWithLMHead.from_pretrained('tsaditya/GPT-Kalki')
>>> text = "ஆதித்த கரிகாலர் தஞ்சைக்குச் செல்ல உடனடியாக ஒப்புக்கொண்டார். "
>>> encoded_text = tokenizer.encode(text, return_tensors='tf')
>>> beam_output = model.generate(
    encoded_text,
    do_sample=True, 
    max_length=512, 
    top_k=50, 
    top_p=0.95, 
    num_return_sequences=1,
    no_repeat_ngram_size = 3,
    temperature = 0.7
    )
>>> print(tokenizer.decode(beam_output[0], skip_special_tokens=True))

📚 Documentation

Model description

GPT2-Kalki is a GPT - 2 transformer model fine - tuned on corpus of Tamil language data from Wikipedia. It has been specifically finetuned on the works of Kalki Krishnamurthy - a Tamil writer from the 1900s. This model is an experimentation of "What if" scenarios using the characters of his novels. The famous movie that has been released now Ponniyin Selvan - I is based on the novel written by the same author. This model is trained on an already trained model on Tamil dataset from [GPT2 - Tamil](https://huggingface.co/abinayam/gpt - 2 - tamil).

Dataset Used

The GTP - 2 model is trained on oscar dataset - ta and IndicNLP dataset - ta and manually scrapped Wikipedia dataset specifically having stories and novels. The scrapped dataset will be released soon.

Widget

• text: 'ஆதித்த கரிகாலர் தஞ்சைக்குச் செல்ல உடனடியாக ஒப்புக்கொண்டார்.'
• text: 'நந்தினி பெரிய பழுவேட்டரையரை உண்மையாக நேசித்தால் '
• text: 'மதுராந்தகருக்கு இராஜ்யமாளும் விருப்பம் இருப்பதாக இல்லை '

🔧 Technical Details

No technical details are provided in the original document.

📄 License

No license information is provided in the original document.