nlp-reranker-finetuned-final / tokenizer_config.json

HPO best: cross-encoder/ms-marco-MiniLM-L-6-v2 | {'num_train_epochs': 1, 'learning_rate': 1.4319807550234704e-06, 'per_device_train_batch_size': 16} | threshold=0.85

0a41a2e verified 11 days ago

raw

history blame contribute delete

453 Bytes

	{
	"backend": "tokenizers",
	"clean_up_tokenization_spaces": true,
	"cls_token": "[CLS]",
	"do_basic_tokenize": true,
	"do_lower_case": true,
	"is_local": false,
	"mask_token": "[MASK]",
	"model_max_length": 512,
	"model_specific_special_tokens": {},
	"never_split": null,
	"pad_token": "[PAD]",
	"sep_token": "[SEP]",
	"strip_accents": null,
	"tokenize_chinese_chars": true,
	"tokenizer_class": "BertTokenizer",
	"unk_token": "[UNK]"
	}