fineweb-edu-classifier-ja / special_tokens_map.json
Kendamarron's picture
Upload folder using huggingface_hub
1fd40ad verified
raw
history blame
1.7 kB
{
"additional_special_tokens": [
{
"content": "<ent>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
{
"content": "<ent2>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
{
"content": "<ent>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
{
"content": "<ent2>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
{
"content": "<ent>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
{
"content": "<ent2>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
{
"content": "<ent>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "<ent2>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "<ent>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
{
"content": "<ent2>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
],
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "<pad>",
"sep_token": "</s>",
"unk_token": "<unk>"
}