bengali-tokenizer / tokenizer_config.json
SaulLu's picture
tokenizer v2- include normalization discussed with Bengali community
9ff1d40
{
"bos_token": "[CLS]",
"eos_token": "[SEP]",
"unk_token": "<unk>",
"sep_token": "[SEP]",
"cls_token": "[CLS]",
"pad_token": "<pad>",
"mask_token": {
"content": "[MASK]",
"single_word": false,
"lstrip": true,
"rstrip": false,
"normalized": true,
"__type": "AddedToken"
},
"model_max_length": 512,
"special_tokens_map_file": null,
"name_or_path": "SaulLu/bengali-tokenizer"
}