Arsh-llm / tokenizer_config.json
arshiaafshani's picture
End of training
13d958f verified
{
"added_tokens_decoder": {
"0": {
"content": "<sos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<|system|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<|user|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<|instruction|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "<|response|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"9": {
"content": "<|separator|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32768": {
"content": "<|eot_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<sos>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|eot_id|>",
"extra_special_tokens": {},
"max_length": 512,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|eot_id|>",
"stride": 0,
"tokenizer_class": "PreTrainedTokenizer",
"trim_offsets": true,
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>"
}