llama8b_sft / tokenizer_config.json
yunjae-won's picture
Update tokenizer_config.json
988d0dd verified
raw
history blame contribute delete
394 Bytes
{
"backend": "tokenizers",
"bos_token": "<|begin_of_text|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|eot_id|>",
"is_local": true,
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 1000000000000000019884624838656,
"model_specific_special_tokens": {},
"pad_token": "<|eot_id|>",
"tokenizer_class": "PreTrainedTokenizerFast"
}