| { | |
| "tokenizer_class": "PreTrainedTokenizerFast", | |
| "model_max_length": 1024, | |
| "bos_token": "<|endoftext|>", | |
| "eos_token": "<|endoftext|>", | |
| "unk_token": null, | |
| "pad_token": "<|pad|>", | |
| "clean_up_tokenization_spaces": false, | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<|endoftext|>", | |
| "special": true, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "single_word": false | |
| }, | |
| "1": { | |
| "content": "<|pad|>", | |
| "special": true, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "single_word": false | |
| }, | |
| "2": { | |
| "content": "<fim_prefix>", | |
| "special": true, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "single_word": false | |
| }, | |
| "3": { | |
| "content": "<fim_middle>", | |
| "special": true, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "single_word": false | |
| }, | |
| "4": { | |
| "content": "<fim_suffix>", | |
| "special": true, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "single_word": false | |
| } | |
| } | |
| } |