finiteautomata
commited on
Commit
•
b41d2b4
1
Parent(s):
a67a88f
Upload tokenizer
Browse files- special_tokens_map.json +9 -1
- tokenizer.json +0 -0
- tokenizer_config.json +13 -1
special_tokens_map.json
CHANGED
@@ -1 +1,9 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
CHANGED
@@ -1 +1,13 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"model_max_length": 128,
|
7 |
+
"name_or_path": "pysentimiento/robertuito-base-uncased",
|
8 |
+
"pad_token": "<pad>",
|
9 |
+
"sep_token": "</s>",
|
10 |
+
"special_tokens_map_file": "models/twerto-base-uncased/special_tokens_map.json",
|
11 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
12 |
+
"unk_token": "<unk>"
|
13 |
+
}
|