{ | |
"add_bos_token": false, | |
"add_prefix_space": false, | |
"additional_special_tokens": [ | |
"<N>", | |
"<MS>", | |
"RB", | |
"VJ" | |
], | |
"bos_token": { | |
"__type": "AddedToken", | |
"content": "<|startoftext|>", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"eos_token": { | |
"__type": "AddedToken", | |
"content": "<|endoftext|>", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"errors": "replace", | |
"model_max_length": 2048, | |
"name_or_path": "EleutherAI/gpt-neo-125M", | |
"pad_token": { | |
"__type": "AddedToken", | |
"content": "<|pad|>", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"special_tokens_map_file": null, | |
"tokenizer_class": "GPT2Tokenizer", | |
"unk_token": { | |
"__type": "AddedToken", | |
"content": "<|endoftext|>", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false | |
} | |
} | |