Views
No views yet
gpt2) model.gpt2-small-dutch-embeddings: Small model size with only retrained lexical embeddings.gpt2-small-dutch: Small model size with retrained lexical embeddings and additional fine-tuning of the full model. (Recommended)gpt2-medium-dutch-embeddings: Medium model size with only retrained lexical embeddings.gpt2-small-italian-embeddings: Small model size with only retrained lexical embeddings.gpt2-small-italian: Small model size with retrained lexical embeddings and additional fine-tuning of the full model. (Recommended)gpt2-medium-italian-embeddings: Medium model size with only retrained lexical embeddings.1from transformers import pipeline
2
3pipe = pipeline("text-generation", model="GroNLP/gpt2-small-italian")1from transformers import AutoTokenizer, AutoModel, TFAutoModel
2
3tokenizer = AutoTokenizer.from_pretrained("GroNLP/gpt2-small-italian")
4model = AutoModel.from_pretrained("GroNLP/gpt2-small-italian") # PyTorch
5model = TFAutoModel.from_pretrained("GroNLP/gpt2-small-italian") # Tensorflow1@misc{devries2020good,
2 title={As good as new. How to successfully recycle English GPT-2 to make models for other languages},
3 author={Wietse de Vries and Malvina Nissim},
4 year={2020},
5 eprint={2012.05628},
6 archivePrefix={arXiv},
7 primaryClass={cs.CL}
8}