17 lines
386 B
JSON
17 lines
386 B
JSON
{
|
|
"backend": "tokenizers",
|
|
"bos_token": "<|begin_of_text|>",
|
|
"clean_up_tokenization_spaces": true,
|
|
"eos_token": "<|eot_id|>",
|
|
"is_local": true,
|
|
"model_input_names": [
|
|
"input_ids",
|
|
"attention_mask"
|
|
],
|
|
"model_max_length": 131072,
|
|
"pad_token": "<|finetune_right_pad_id|>",
|
|
"padding_side": "left",
|
|
"tokenizer_class": "TokenizersBackend",
|
|
"unk_token": null
|
|
}
|