Upload tokenizer
#2
by
ArthurZ
HF Staff
- opened
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": "<mask>",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "</s>",
|
| 8 |
+
"unk_token": "[UNK]"
|
| 9 |
+
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {},
|
| 3 |
+
"additional_special_tokens": [],
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": true,
|
| 6 |
+
"cls_token": "<s>",
|
| 7 |
+
"do_lower_case": true,
|
| 8 |
+
"eos_token": "</s>",
|
| 9 |
+
"mask_token": "<mask>",
|
| 10 |
+
"model_max_length": 512,
|
| 11 |
+
"pad_token": "<pad>",
|
| 12 |
+
"sep_token": "</s>",
|
| 13 |
+
"strip_accents": null,
|
| 14 |
+
"tokenize_chinese_chars": true,
|
| 15 |
+
"tokenizer_class": "MPNetTokenizer",
|
| 16 |
+
"unk_token": "[UNK]"
|
| 17 |
+
}
|