| from transformers import GPT2LMHeadModel, GPT2Tokenizer | |
| # Load the pre-trained model and tokenizer | |
| tokenizer = GPT2Tokenizer.from_pretrained("sberbank-ai/mGPT") | |
| model = GPT2LMHeadModel.from_pretrained("sberbank-ai/mGPT") | |
| # Input text | |
| text = "Александр Сергеевич Пушкин родился в " | |
| # Encode the input text | |
| input_ids = tokenizer.encode(text, return_tensors="pt") | |
| # Generate text | |
| out = model.generate( | |
| input_ids, | |
| min_length=100, | |
| max_length=100, | |
| eos_token_id=5, | |
| pad_token_id=1, | |
| top_k=10, | |
| top_p=0.0, | |
| no_repeat_ngram_size=5 | |
| ) | |
| # Decode the generated output | |
| generated_text = list(map(tokenizer.decode, out))[0] | |
| print(generated_text) | |