Adding precomputed fast-tokenizer.
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +11 -2
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"]}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,3 +1,12 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"sep_token": "</s>",
|
5 |
+
"cls_token": "<s>",
|
6 |
+
"unk_token": "<unk>",
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"mask_token": "<mask>",
|
9 |
+
"additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"],
|
10 |
+
"do_lower_case": true,
|
11 |
+
"special_tokens_map_file": null
|
12 |
+
}
|