gpt2_dad_joke_tokenizer / tokenizer_config.json
abhirajeshbhai's picture
Upload tokenizer
ddb4ece
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50257": {
"content": "<pad>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"50258": {
"content": "<bos>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"50259": {
"content": "<eos>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"50260": {
"content": "JOKE:",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [],
"bos_token": "<bos>",
"clean_up_tokenization_spaces": true,
"eos_token": "<eos>",
"errors": "replace",
"model_max_length": 1024,
"pad_token": "<pad>",
"tokenizer_class": "GPT2Tokenizer",
"tokenizer_file": "/root/.cache/huggingface/hub/models--gpt2/snapshots/11c5a3d5811f50298f278a704980280950aedb10/tokenizer.json",
"unk_token": "<|endoftext|>"
}