21 lines
464 B
JSON
21 lines
464 B
JSON
|
{
|
||
|
|
"backend": "tokenizers",
|
||
|
|
"bos_token": "<|begin_of_text|>",
|
||
|
|
"clean_up_tokenization_spaces": true,
|
||
|
|
"eos_token": "<|eot_id|>",
|
||
|
|
"extra_special_tokens": [
|
||
|
|
"<|eom_id|>"
|
||
|
|
],
|
||
|
|
"is_local": false,
|
||
|
|
"local_files_only": false,
|
||
|
|
"model_input_names": [
|
||
|
|
"input_ids",
|
||
|
|
"attention_mask"
|
||
|
|
],
|
||
|
|
"model_max_length": 131072,
|
||
|
|
"pad_token": "<|eot_id|>",
|
||
|
|
"padding_side": "right",
|
||
|
|
"split_special_tokens": false,
|
||
|
|
"tokenizer_class": "TokenizersBackend"
|
||
|
|
}
|