marianmt-tatoeba-enru / tokenizer_config.json
adorkin's picture
add tokenizer
67363ca
raw
history blame
No virus
317 Bytes
{"source_lang": "en", "target_lang": "ru", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/home/adorkin/tmp/tatoeba_enru/checkpoint-59990", "tokenizer_class": "MarianTokenizer"}