cantonesellm-cpt-202405 / special_tokens_map.json
indiejoseph's picture
Training in progress, step 100
cc54c06 verified
raw
history blame
704 Bytes
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|Human|>",
"<|Assistant|>",
"<|System|>"
],
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}