{ "source": "allenai/c4", "config": "en", "split": "train", "model_type": "unigram", "vocab_size": 32000, "lowercase": true, "normalization": "NFKC + SentencePiece nmt_nfkc", "training_text_bytes": 536874807, "training_documents": 247312, "special_token_ids": { "": 0, "": 1, "": 2, "": 3, "": 4, "": 5, "": 6 }, "sha256_spiece_model": "119ec6b2af9cbbc56f297bd606b69f79f6e3130a34ee56122ee813a58d15bb9d" }