| { | |
| "add_prefix_space": false, | |
| "additional_special_tokens": [ | |
| "<|endoftext|>", | |
| "<fim_prefix>", | |
| "<fim_middle>", | |
| "<fim_suffix>", | |
| "<fim_pad>", | |
| "<filename>", | |
| "<gh_stars>", | |
| "<issue_start>", | |
| "<issue_comment>", | |
| "<issue_closed>", | |
| "<jupyter_start>", | |
| "<jupyter_text>", | |
| "<jupyter_code>", | |
| "<jupyter_output>", | |
| "<empty_output>", | |
| "<commit_before>", | |
| "<commit_msg>", | |
| "<commit_after>", | |
| "<reponame>" | |
| ], | |
| "bos_token": "<|endoftext|>", | |
| "clean_up_tokenization_spaces": true, | |
| "eos_token": "<|endoftext|>", | |
| "model_max_length": 2048, | |
| "padding_side": "right", | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "unk_token": "<|endoftext|>", | |
| "vocab_size": 49152 | |
| } | |