| { |
| "add_bos_token": false, |
| "add_eos_token": true, |
| "add_prefix_space": false, |
| "added_tokens_decoder": { |
| "50256": { |
| "content": "<|endoftext|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50257": { |
| "content": "[PAD]", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50258": { |
| "content": "<sos>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50259": { |
| "content": "<eos>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| } |
| }, |
| "additional_special_tokens": [ |
| "<sos>", |
| "<eos>" |
| ], |
| "bos_token": "<|endoftext|>", |
| "clean_up_tokenization_spaces": true, |
| "eos_token": "<|endoftext|>", |
| "errors": "replace", |
| "max_length": 512, |
| "model_max_length": 512, |
| "pad_token": "<|endoftext|>", |
| "padding_side": "right", |
| "stride": 0, |
| "tokenizer_class": "GPT2Tokenizer", |
| "truncation_side": "right", |
| "truncation_strategy": "longest_first", |
| "unk_token": "<|endoftext|>" |
| } |
|
|
