Views
No views yet
| Attribute | Details |
|---|---|
| Base Model | GPT-2 (124M) |
| Architecture | Decoder-only Transformer |
| Framework | TensorFlow / KerasNLP |
| Dataset | Bhagavad Gita (English meanings) |
| Languages | English |
| Dataset Size | ~700 verses |
| Tokenizer | GPT-2 tokenizer (inherited vocabulary) |
transformers:1from transformers import AutoTokenizer, AutoModelForCausalLM
2
3# Load tokenizer & model
4tokenizer = AutoTokenizer.from_pretrained("AP6621/Bhagawatgitagpt")
5model = AutoModelForCausalLM.from_pretrained("AP6621/Bhagawatgitagpt")
6
7# Generate text
8inputs = tokenizer("Arjuna asked:", return_tensors="pt")
9outputs = model.generate(**inputs, max_length=100, do_sample=True, top_p=0.9, temperature=0.8)
10
11print(tokenizer.decode(outputs[0], skip_special_tokens=True))Arjuna asked:1@misc{gpt2-bhagavadgita,
2 title = {Fine-tuned GPT-2 on Bhagavad Gita Dataset},
3 author = {Your Name},
4 year = {2025},
5 publisher = {Hugging Face},
6 howpublished = {\url{https://huggingface.co/your-username/gpt2-bhagavad-gita}}
7}