luinllm / tokenizer_config.json
percisestretch's picture
luinllm
ffb1a60
Raw History Blame Contribute Delete
615 Bytes
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"is_local": true,
"model_max_length": 262144,
"pad_token": "<|endoftext|>",
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
"split_special_tokens": false,
"tokenizer_class": "TokenizersBackend",
"unk_token": null,
"_luinllm_changes": "Modified deployment configuration: unused multimodal metadata removed."
}