Commit
·
b3d8f12
1
Parent(s):
f966a60
Upload tokenizer
Browse files- special_tokens_map.json +5 -0
- tokenizer.json +3 -3
- tokenizer_config.json +5 -1
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,9 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"eos_token": "</s>",
|
| 4 |
"unk_token": "<unk>"
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
"bos_token": "<s>",
|
| 8 |
"eos_token": "</s>",
|
| 9 |
"unk_token": "<unk>"
|
tokenizer.json
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
-
"normalized":
|
| 13 |
"special": true
|
| 14 |
},
|
| 15 |
{
|
|
@@ -18,7 +18,7 @@
|
|
| 18 |
"single_word": false,
|
| 19 |
"lstrip": false,
|
| 20 |
"rstrip": false,
|
| 21 |
-
"normalized":
|
| 22 |
"special": true
|
| 23 |
},
|
| 24 |
{
|
|
@@ -27,7 +27,7 @@
|
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
-
"normalized":
|
| 31 |
"special": true
|
| 32 |
}
|
| 33 |
],
|
|
|
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
"special": true
|
| 14 |
},
|
| 15 |
{
|
|
|
|
| 18 |
"single_word": false,
|
| 19 |
"lstrip": false,
|
| 20 |
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
"special": true
|
| 23 |
},
|
| 24 |
{
|
|
|
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
}
|
| 33 |
],
|
tokenizer_config.json
CHANGED
|
@@ -27,7 +27,11 @@
|
|
| 27 |
"special": true
|
| 28 |
}
|
| 29 |
},
|
| 30 |
-
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
"bos_token": "<s>",
|
| 32 |
"clean_up_tokenization_spaces": false,
|
| 33 |
"eos_token": "</s>",
|
|
|
|
| 27 |
"special": true
|
| 28 |
}
|
| 29 |
},
|
| 30 |
+
"additional_special_tokens": [
|
| 31 |
+
"<unk>",
|
| 32 |
+
"<s>",
|
| 33 |
+
"</s>"
|
| 34 |
+
],
|
| 35 |
"bos_token": "<s>",
|
| 36 |
"clean_up_tokenization_spaces": false,
|
| 37 |
"eos_token": "</s>",
|