simple-tokenizer-5120 / tokenizer_config.json
ddh0's picture
Upload folder using huggingface_hub
7b207e0 verified
{
"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": "<|SYSTEM|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<|USER|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<|ASSISTANT|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|BOS|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|EOS|>",
"extra_special_tokens": {},
"model_max_length": 1073741824,
"pad_token": "<|PAD|>",
"tokenizer_class": "PreTrainedTokenizerFast"
}