| { | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "[PAD]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "[BOS]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "[EOS]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "6": { | |
| "content": "N", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| } | |
| }, | |
| "auto_map": { | |
| "AutoTokenizer": [ | |
| null, | |
| "tokenization_microglot.MicroGlotTokenizerFast" | |
| ] | |
| }, | |
| "bos_token": "[BOS]", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "[EOS]", | |
| "extra_special_tokens": {}, | |
| "model_input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "model_max_length": 8192, | |
| "pad_token": "[PAD]", | |
| "padding_side": "right", | |
| "tokenizer_class": "MicroGlotTokenizerFast", | |
| "vocab_size": 8192 | |
| } | |