BAAI-AquilaChat2-7B-bnb-8bit-smashed / tokenizer_config.json
sharpenb's picture
736b09e13b4dfc4d273161eb219da547da1bdc85536039b5bd1c3f460552e0ac
fc69c5e verified
raw
history blame
1.91 kB
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100000": {
"content": "<|startofpiece|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"100001": {
"content": "<|endofpiece|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"100002": {
"content": "<|LDWANG|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"100003": {
"content": "[MASK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"100004": {
"content": "[gMASK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"100005": {
"content": "[sMASK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"100006": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100007": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "[CLS]",
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 2048,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}