LUKE-Marian-Model-on-CoNaLa / tokenizer_config.json
AhmedSSoliman's picture
Upload tokenizer_config.json
a211b63
raw
history blame
1.81 kB
{"errors": "replace", "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "task": null, "max_entity_length": 32, "max_mention_length": 30, "entity_token_1": "<ent>", "entity_token_2": "<ent2>", "entity_unk_token": "[UNK]", "entity_pad_token": "[PAD]", "entity_mask_token": "[MASK]", "entity_mask2_token": "[MASK2]", "model_max_length": 512, "name_or_path": "studio-ousia/luke-base", "special_tokens_map_file": "/root/.cache/huggingface/transformers/e2adf9c43ab82e2db47210f87bb53aa544055afc59e35389ffff22cd8fbd5d94.0ead83d1c22a0d79f17fc2eb3b32bd99fd9a262049166681d9713840ae868c2a", "additional_special_tokens": [{"content": "<ent>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, {"content": "<ent2>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}], "tokenizer_class": "LukeTokenizer"}