55 lines
1.1 KiB
JSON
55 lines
1.1 KiB
JSON
{
|
|
"added_tokens_decoder": {
|
|
"0": {
|
|
"content": "<|endoftext|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"1": {
|
|
"content": "<|im_start|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"2": {
|
|
"content": "<|im_end|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"3": {
|
|
"content": "<|pad|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"additional_special_tokens": [
|
|
"<|im_start|>",
|
|
"<|im_end|>"
|
|
],
|
|
"bos_token": null,
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "<|endoftext|>",
|
|
"extra_special_tokens": {},
|
|
"model_max_length": 4096,
|
|
"pad_token": "<|pad|>",
|
|
"padding_side": "left",
|
|
"tokenizer_class": "PreTrainedTokenizerFast",
|
|
"truncation_side": "left",
|
|
"unk_token": null,
|
|
"model_input_names": [
|
|
"input_ids",
|
|
"attention_mask"
|
|
]
|
|
}
|