Fix tokenizer files

This commit is contained in:
Niels Rogge 2022-01-19 17:03:47 +01:00
parent dcf3033e95
commit 18d30d29a8
3 changed files with 20 additions and 30673 deletions

18
preprocessor_config.json Normal file
View File

@ -0,0 +1,18 @@
{
"do_normalize": true,
"do_resize": true,
"feature_extractor_type": "ViltFeatureExtractor",
"image_mean": [
0.5,
0.5,
0.5
],
"image_std": [
0.5,
0.5,
0.5
],
"resample": 3,
"size": 384,
"size_divisor": 32
}

File diff suppressed because one or more lines are too long

View File

@ -1 +1 @@
{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/534479488c54aeaf9c3406f647aa2ec13648c06771ffe269edabebd4c412da1d.7f2721073f19841be16f41b0a70b600ca6b880c8f3df6f3535cbc704371bdfa4", "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}