RFamLlama-base / tokenizer_config.json
jinyuan22's picture
Upload 6 files
82645da verified
raw
history blame
1.45 kB
{
"added_tokens_decoder": {
"0": {
"content": "<|pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|bos|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|eos|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<|tag_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"4": {
"content": "<|tag_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"5": {
"content": "<|5|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"6": {
"content": "<|3|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
}
},
"bos_token": "<|bos|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|eos|>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|pad|>",
"tokenizer_class": "PreTrainedTokenizerFast"
}