Files
Boldt-DC-350M/tokenizer_config.json
ModelHub XC 1568492ba3 初始化项目,由ModelHub XC社区提供模型
Model: Boldt/Boldt-DC-350M
Source: Original Platform
2026-05-22 10:04:17 +08:00

30 lines
666 B
JSON

{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 2048,
"pad_token": "<|pad|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}