colbert-citras / tokenizer_config.json
bowang0911's picture
Upload folder using huggingface_hub
dfdca26 verified
raw
history blame contribute delete
480 Bytes
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"is_local": false,
"mask_token": "\u00e2\u00bd\u0139",
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"sep_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null,
"additional_special_tokens": [
"[Q]",
"[D]"
]
}