Upload processor
Browse files
qformer_tokenizer/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[DEC]": 30522
|
| 3 |
+
}
|
qformer_tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[DEC]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"mask_token": "[MASK]",
|
| 5 |
+
"pad_token": "[PAD]",
|
| 6 |
+
"sep_token": "[SEP]",
|
| 7 |
+
"unk_token": "[UNK]"
|
| 8 |
+
}
|
qformer_tokenizer/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qformer_tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"strip_accents": null,
|
| 10 |
+
"tokenize_chinese_chars": true,
|
| 11 |
+
"tokenizer_class": "BertTokenizer",
|
| 12 |
+
"truncation_side": "left",
|
| 13 |
+
"unk_token": "[UNK]"
|
| 14 |
+
}
|
qformer_tokenizer/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|