| { | |
| "add_bos_token": true, | |
| "add_eos_token": false, | |
| "added_tokens_decoder": { | |
| "100000": { | |
| "content": "<｜begin▁of▁sentence｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "100001": { | |
| "content": "<｜end▁of▁sentence｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "100002": { | |
| "content": "[PAD]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "100003": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "bos_token": "<｜begin▁of▁sentence｜>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<｜end▁of▁sentence｜>", | |
| "legacy": true, | |
| "max_length": 4096, | |
| "model_max_length": 4096, | |
| "pad_token": "[PAD]", | |
| "padding_side": "left", | |
| "sp_model_kwargs": {}, | |
| "stride": 0, | |
| "tokenizer_class": "LlamaTokenizer", | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first", | |
| "unk_token": "<unk>", | |
| "use_default_system_prompt": false | |
| } | |