| { | |
| "add_bos_token": true, | |
| "add_eos_token": false, | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "auto_map": { | |
| "AutoTokenizer": [ | |
| "tokenization_internlm2.InternLM2Tokenizer", | |
| "tokenization_internlm2_fast.InternLM2TokenizerFast" | |
| ] | |
| }, | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": false, | |
| "decode_with_prefix_space": false, | |
| "eos_token": "</s>", | |
| "max_length": 3, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_to_multiple_of": null, | |
| "pad_token": "</s>", | |
| "pad_token_type_id": 0, | |
| "padding_side": "left", | |
| "sp_model_kwargs": null, | |
| "stride": 0, | |
| "tokenizer_class": "InternLM2Tokenizer", | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first", | |
| "unk_token": "<unk>" | |
| } | |