greenleaf-law-embed-tiny / tokenizer_config.json
sakasurya's picture
judicialmind/greenleaf-law-embed-tiny: initial release
bff06c9
Raw
History Blame Contribute Delete
627 Bytes
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"is_local": true,
"local_files_only": false,
"mask_token": "â½Ĺ",
"max_length": 256,
"model_max_length": 1024,
"pad_to_multiple_of": null,
"pad_token": "<|endoftext|>",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "<|endoftext|>",
"split_special_tokens": false,
"stride": 0,
"tokenizer_class": "Qwen2Tokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": null
}