| { | |
| "add_bos_token": true, | |
| "add_prefix_space": false, | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50265": { | |
| "content": "<|im_end|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50266": { | |
| "content": "<|im_start|>user", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50267": { | |
| "content": "<|im_start|>assistant", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50268": { | |
| "content": "<|im_start|>system", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "additional_special_tokens": [ | |
| "<|im_start|>user", | |
| "<|im_start|>assistant", | |
| "<|im_start|>system", | |
| "<|im_end|>", | |
| "<s>", | |
| "<pad>" | |
| ], | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": true, | |
| "eos_token": "<|im_end|>", | |
| "errors": "replace", | |
| "model_max_length": 100, | |
| "pad_token": "<pad>", | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "unk_token": "</s>" | |
| } | |