GroNLP/gpt2-medium-dutch-embeddings

This model is based on the medium OpenAI GPT-2 (gpt2-medium) model . Transformer layer weights in this model are identical to the original English, model but the lexical layer has been retrained for a Dutch vocabulary . For details, check out our paper on arXiv and the code on Github . The model is available in PyTorch and Tensorflow on the open-source platform . For more information, please visit the ArXiv paper and Github page: recycled for Dutch (Gpt-2 recycled for Dutch, adapted lexical embeddings, or Gpt2 for Italian (adapted for Italian, adapted for Dutch,