dgt-mt-hu-ro / tokenizer_config.json

Added all files from model checkpoint-62500 for vocab_size 20000, 10 epochs

732ed89 over 1 year ago

No virus

318 Bytes

	{
	"eos_token": "</s>",
	"model_max_length": 512,
	"name_or_path": "marian-mt-hu-ro-20000",
	"pad_token": "<pad>",
	"separate_vocabs": false,
	"source_lang": null,
	"sp_model_kwargs": {},
	"special_tokens_map_file": null,
	"target_lang": null,
	"tokenizer_class": "MarianTokenizer",
	"unk_token": "<unk>"
	}