interlinear-en-philta-emb-auto-diacritics-bh / morph_tokenizer_config.json
mrapacz's picture
Upload tokenizer
816560e verified
raw
history blame contribute delete
173 Bytes
{"morph_encodings": {}, "special_tokens_map": {"pad_token": "<pad>", "eos_token": "<eos>", "unk_token": "<unk>", "block_separator_token": "<extra_id_0>"}, "unique_tags": []}