Upload tokenizer
Browse files- special_tokens_map.json +9 -0
- spiece.model +3 -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": "[CLS]",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "[UNK]"
|
9 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d78ab344146700112cd41628ac7ce54b79c0868fe0c7c201750d8237b54dbb4
|
3 |
+
size 786216
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"additional_special_tokens": [],
|
4 |
+
"bos_token": "<s>",
|
5 |
+
"clean_up_tokenization_spaces": true,
|
6 |
+
"cls_token": "[CLS]",
|
7 |
+
"do_lower_case": false,
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"extra_ids": 0,
|
10 |
+
"mask_token": "[MASK]",
|
11 |
+
"model_max_length": 1000000000000000019884624838656,
|
12 |
+
"pad_token": "[PAD]",
|
13 |
+
"sep_token": "[SEP]",
|
14 |
+
"sp_model_kwargs": {},
|
15 |
+
"tokenizer_class": "T5Tokenizer",
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|