Commit
•
b883cad
1
Parent(s):
d24a003
Upload tokenizer
Browse files- special_tokens_map.json +0 -9
- tokenizer_config.json +0 -11
special_tokens_map.json
CHANGED
|
@@ -1,13 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
{
|
| 4 |
-
"content": "<SOH>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false
|
| 9 |
-
}
|
| 10 |
-
],
|
| 11 |
"bos_token": {
|
| 12 |
"content": "<s>",
|
| 13 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -25,19 +25,8 @@
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
-
},
|
| 29 |
-
"32000": {
|
| 30 |
-
"content": "<SOH>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
}
|
| 37 |
},
|
| 38 |
-
"additional_special_tokens": [
|
| 39 |
-
"<SOH>"
|
| 40 |
-
],
|
| 41 |
"bos_token": "<s>",
|
| 42 |
"clean_up_tokenization_spaces": false,
|
| 43 |
"eos_token": "</s>",
|
|
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
}
|
| 29 |
},
|
|
|
|
|
|
|
|
|
|
| 30 |
"bos_token": "<s>",
|
| 31 |
"clean_up_tokenization_spaces": false,
|
| 32 |
"eos_token": "</s>",
|