ja-en-dataset-v3.0-subset-v3.0 / tokenizer_config.json
Prgrg's picture
Training in progress epoch 0
aa7316b
raw
history blame
No virus
380 Bytes
{
"access_token": "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",
"eos_token": "</s>",
"model_max_length": 512,
"pad_token": "<pad>",
"private": true,
"return_tensors": "pt",
"separate_vocabs": false,
"source_lang": "jap",
"sp_model_kwargs": {},
"special_tokens_map_file": null,
"target_lang": "en",
"tokenizer_class": "MarianTokenizer",
"unk_token": "<unk>"
}