bolbolzaban/gpt2-persian

GPT2-Persian is gpt2 language model that is trained with hyper parameters similar to standard gpt-pt2-medium . All non-persian characters are replaced with especial tokens (e.g [LAT], [URL], [NUM) The context size is reduced from 1024 to 256 sub words in order to make the training affordable . Instead of BPE, google sentence piece tokenizor is used for tokenization . The training dataset only include Persian text . The model is trained for the purpose of research on Persian poetry . If you want to use classical Persian poetry as input use [BOM] (begining of mesra) at the beginning of,