llama2-13b-megacode2-oasst / tokenizer_config.json
andreaskoepf's picture
use <|im_start> as bos and <|im_end|> as eos tokens
f498ce7
raw
history blame
740 Bytes
{
"bos_token": {
"__type": "AddedToken",
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}