| Model card for RoGPT2-medium | |
| --- | |
| language: | |
| - ro | |
| --- | |
| # RoGPT2: Romanian GPT2 for text generation | |
| All models are available: | |
| * [RoBERT-base](https://huggingface.co/readerbench/RoGPT2-base) | |
| * [RoBERT-medium](https://huggingface.co/readerbench/RoGPT2-medium) | |
| * [RoBERT-large](https://huggingface.co/readerbench/RoGPT2-large) | |
| #### How to use | |
| ```python | |
| from transformers import AutoTokenizer, TFAutoModelWithLMHead | |
| tokenizer = AutoTokenizer.from_pretrained('readerbench/RoGPT2-medium') | |
| model = TFAutoModelWithLMHead.from_pretrained('readerbench/RoGPT2-medium') | |
| inputs = tokenizer.encode("Este o zi de vara", return_tensors='tf') | |
| text = model.generate(inputs, max_length=1024, no_repeat_ngram_size=2) | |
| print(tokenizer.decode(text[0])) | |
| ``` | |