Commit
•
05f8a1b
1
Parent(s):
c8195cc
Upload tokenizer
Browse files- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +19 -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
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"mask_token": "<mask>",
|
| 7 |
+
"max_length": 128,
|
| 8 |
+
"model_max_length": 128,
|
| 9 |
+
"pad_to_multiple_of": null,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"pad_token_type_id": 0,
|
| 12 |
+
"padding_side": "right",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"stride": 0,
|
| 15 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 16 |
+
"truncation_side": "right",
|
| 17 |
+
"truncation_strategy": "longest_first",
|
| 18 |
+
"unk_token": "<unk>"
|
| 19 |
+
}
|