FinewebVi-Qwen3Next / tokenizer_config.json
thng292's picture
Upload tokenizer
188e055 verified
{
"added_tokens_decoder": {
"0": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65536": {
"content": "<|unk|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65537": {
"content": "<|reserved_special_token_0|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"65538": {
"content": "<|reserved_special_token_1|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"65539": {
"content": "<|reserved_special_token_2|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"65540": {
"content": "<|reserved_special_token_3|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"65541": {
"content": "<|reserved_special_token_4|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"65542": {
"content": "<|reserved_special_token_5|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"65543": {
"content": "<|reserved_special_token_6|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"65544": {
"content": "<|reserved_special_token_7|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"65545": {
"content": "<|reserved_special_token_8|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"65546": {
"content": "<|reserved_special_token_9|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"65547": {
"content": "<|reserved_special_token_10|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"65548": {
"content": "<|reserved_special_token_11|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"65549": {
"content": "<|reserved_special_token_12|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<|end_of_text|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|end_of_text|>",
"extra_special_tokens": {},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|end_of_text|>",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<|unk|>"
}