Tereveni-AI/gpt2-124M-uk-fiction

GPT2 124M Trained on Ukranian Fiction has been trained on corpus of 4040 fiction books, 2.77 GiB in total . Evaluation on brown-uk gives perplexity of 50.16.6 GiB . The default code snippet above won't work because we are using AlbertTokenizer with Gpt2LMHeadModel, see issue issue issue. [Note: default code snippets above won’t work because of Albert tokenizer and GPTLM head model. see issue.org/gpt2-124M-uk-fiction.iopiopio.iopio . For example, the default code will be print: print(i),