NuExtract-tiny-Resume-Data-Extractor / tokenizer_config.json
nimendraai's picture
Upload tokenizer
d4b5e4d verified
raw
history blame contribute delete
517 Bytes
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"extra_special_tokens": [],
"is_local": false,
"max_length": 2500,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "left",
"split_special_tokens": false,
"stride": 0,
"tokenizer_class": "Qwen2Tokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": null
}