donut-commoncrawl / special_tokens_map.json
laverdes's picture
End of training
4f5f119
raw
history blame
1.23 kB
{
"additional_special_tokens": [
"<s_Text>\n",
"</s_Text>\n",
"<s_Subheadline>\n",
"</s_Subheadline>\n",
"<s_Picture>\n",
"</s_Picture>\n",
"<s_Misc>\n",
"</s_Misc>\n",
"<s_List-item>\n",
"</s_List-item>\n",
"<s_List>\n",
"</s_List>\n",
"<s_Headline>\n",
"</s_Headline>\n",
"<s_Author>\n",
"</s_Author>\n",
"<s_Header>\n",
"</s_Header>\n",
"<s_Caption>\n",
"</s_Caption>\n",
"<s_Table>\n",
"</s_Table>\n",
"<s_Footer>\n",
"</s_Footer>\n",
"<s_Address>\n",
"</s_Address>\n",
"<s_Title>\n",
"</s_Title>\n",
"<s_Abstract>\n",
"</s_Abstract>\n",
"<s_Value>\n",
"</s_Value>\n",
"<s_Metadata>\n",
"</s_Metadata>\n",
"<s_Field-Name>\n",
"</s_Field-Name>\n",
"<s_Link>\n",
"</s_Link>\n",
"<s_Advertisement>\n",
"</s_Advertisement>\n",
"<s_Form>\n",
"</s_Form>\n",
"<s>",
"</s>"
],
"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>"
}