| { |
| "add_bos_token": false, |
| "add_prefix_space": true, |
| "added_tokens_decoder": { |
| "50265": { |
| "content": "<|endoftext|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50266": { |
| "content": "<|startoftext|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50267": { |
| "content": "<|pad|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50268": { |
| "content": "<|unk|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| } |
| }, |
| "bos_token": "<|startoftext|>", |
| "clean_up_tokenization_spaces": true, |
| "eos_token": "<|endoftext|>", |
| "errors": "replace", |
| "model_max_length": 1000000000000000019884624838656, |
| "pad_token": "<|pad|>", |
| "tokenizer_class": "GPT2Tokenizer", |
| "unk_token": "<|unk|>" |
| } |
|
|
