llm-jp-3-13b-october-news-e1-all-3-5 / tokenizer_config.json
ikedachin's picture
Trained with Unsloth
f95452d verified
raw
history blame
1.86 kB
{
"add_bos_token": true,
"add_eos_token": false,
"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
},
"3": {
"content": "<MASK|LLM-jp>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<PAD|LLM-jp>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<CLS|LLM-jp>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<SEP|LLM-jp>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<EOD|LLM-jp>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": "<CLS|LLM-jp>",
"eod_token": "</s>",
"eos_token": "</s>",
"extra_ids": 0,
"mask_token": "<MASK|LLM-jp>",
"model_max_length": 4096,
"pad_token": "<PAD|LLM-jp>",
"padding_side": "left",
"sep_token": "<SEP|LLM-jp>",
"sp_model_kwargs": {},
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<unk>"
}