nep-tokenizer / tokenizer_config.json

Release Nep-Tokenizer v2 (64k): Native Hugging Face BPE with Mark-Aware Pre-tokenization and 100% Devanagari Block Coverage

a4c3ef3 about 22 hours ago

Raw History Blame Contribute Delete

272 Bytes

{
  "backend": "tokenizers",
  "bos_token": "<|bos|>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|eos|>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<|pad|>",
  "tokenizer_class": "TokenizersBackend",
  "unk_token": "<|unk|>"
}

	{
	"backend": "tokenizers",
	"bos_token": "<\|bos\|>",
	"clean_up_tokenization_spaces": false,
	"eos_token": "<\|eos\|>",
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<\|pad\|>",
	"tokenizer_class": "TokenizersBackend",
	"unk_token": "<\|unk\|>"
	}