35 lines
721 B
JSON
35 lines
721 B
JSON
|
{
|
||
|
|
"backend": "tokenizers",
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"do_lower_case": false,
|
||
|
|
"eos_token": "<|endoftext|>",
|
||
|
|
"extra_special_tokens": [
|
||
|
|
"<|endoftext|>",
|
||
|
|
"[MASK]",
|
||
|
|
"[gMASK]",
|
||
|
|
"[sMASK]",
|
||
|
|
"<sop>",
|
||
|
|
"<eop>",
|
||
|
|
"<|system|>",
|
||
|
|
"<|user|>",
|
||
|
|
"<|assistant|>",
|
||
|
|
"<|observation|>",
|
||
|
|
"<|begin_of_image|>",
|
||
|
|
"<|end_of_image|>",
|
||
|
|
"<|begin_of_video|>",
|
||
|
|
"<|end_of_video|>"
|
||
|
|
],
|
||
|
|
"image_size": 448,
|
||
|
|
"is_local": true,
|
||
|
|
"local_files_only": false,
|
||
|
|
"model_input_names": [
|
||
|
|
"input_ids",
|
||
|
|
"attention_mask"
|
||
|
|
],
|
||
|
|
"model_max_length": 8192,
|
||
|
|
"pad_token": "<|endoftext|>",
|
||
|
|
"padding_side": "left",
|
||
|
|
"remove_space": false,
|
||
|
|
"tokenizer_class": "TokenizersBackend"
|
||
|
|
}
|