180 lines
3.8 KiB
JSON
180 lines
3.8 KiB
JSON
{
|
|
"added_tokens_decoder": {
|
|
"0": {
|
|
"content": "<|endoftext|>",
|
|
"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": "<|unk|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"3": {
|
|
"content": "<|bos|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"4": {
|
|
"content": "<|eos|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"5": {
|
|
"content": "<|im_start|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"6": {
|
|
"content": "<|im_end|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"7": {
|
|
"content": "<|im_sep|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"8": {
|
|
"content": "<|special_0|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"9": {
|
|
"content": "<|special_1|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"10": {
|
|
"content": "<|special_2|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"11": {
|
|
"content": "<|special_3|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"12": {
|
|
"content": "<|special_4|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"13": {
|
|
"content": "<|special_5|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"14": {
|
|
"content": "<|special_6|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"15": {
|
|
"content": "<|special_7|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"16": {
|
|
"content": "<|special_8|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"17": {
|
|
"content": "<|special_9|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"additional_special_tokens": [
|
|
"<|im_start|>",
|
|
"<|im_end|>",
|
|
"<|im_sep|>",
|
|
"<|special_0|>",
|
|
"<|special_1|>",
|
|
"<|special_2|>",
|
|
"<|special_3|>",
|
|
"<|special_4|>",
|
|
"<|special_5|>",
|
|
"<|special_6|>",
|
|
"<|special_7|>",
|
|
"<|special_8|>",
|
|
"<|special_9|>"
|
|
],
|
|
"bos_token": "<|bos|>",
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "<|im_end|>",
|
|
"extra_special_tokens": {},
|
|
"max_length": 2048,
|
|
"model_max_length": 8192,
|
|
"pad_token": "<|pad|>",
|
|
"stride": 0,
|
|
"tokenizer_class": "PreTrainedTokenizerFast",
|
|
"truncation_side": "right",
|
|
"truncation_strategy": "longest_first",
|
|
"unk_token": "<|unk|>",
|
|
"return_token_type_ids": false,
|
|
"model_input_names": [
|
|
"input_ids",
|
|
"attention_mask"
|
|
]
|
|
} |