36 lines
836 B
JSON
36 lines
836 B
JSON
|
{
|
||
|
|
"add_bos_token": true,
|
||
|
|
"add_eos_token": false,
|
||
|
|
"bos_token": {
|
||
|
|
"__type": "AddedToken",
|
||
|
|
"content": "<s>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"eos_token": {
|
||
|
|
"__type": "AddedToken",
|
||
|
|
"content": "</s>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
"model_max_length": 512,
|
||
|
|
"pad_token": null,
|
||
|
|
"padding_side": "right",
|
||
|
|
"sp_model_kwargs": {},
|
||
|
|
"special_tokens_map_file": "/juice5/scr5/nlp/llama_model/llama_hf_latest/llama-7b/special_tokens_map.json",
|
||
|
|
"tokenizer_class": "LlamaTokenizer",
|
||
|
|
"unk_token": {
|
||
|
|
"__type": "AddedToken",
|
||
|
|
"content": "<unk>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
}
|
||
|
|
}
|