longformer-simple / checkpoint-2511 /tokenizer_config.json
Theoreticallyhugo's picture
Training in progress, epoch 31, checkpoint
ff5a74e verified
raw
history blame
1.22 kB
{
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50264": {
"content": "<mask>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"mask_token": "<mask>",
"model_max_length": 4096,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "LongformerTokenizer",
"trim_offsets": true,
"unk_token": "<unk>"
}