nuph-tokenizer / tokenizer_config.json
baebee's picture
Upload folder using huggingface_hub
2406558
{
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<|system|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32001": {
"content": "<|response|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32002": {
"content": "<|prompt|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|system|>",
"<|response|>",
"<|prompt|>"
],
"bos_token": "<|im_start|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": true
}