Commit
•
1a39040
1
Parent(s):
752471b
Upload tokenizer
Browse files- special_tokens_map.json +6 -6
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
special_tokens_map.json
CHANGED
|
@@ -1,22 +1,22 @@
|
|
| 1 |
{
|
| 2 |
"bos_token": {
|
| 3 |
-
"content": "
|
| 4 |
"lstrip": false,
|
| 5 |
-
"normalized":
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
-
"content": "
|
| 11 |
"lstrip": false,
|
| 12 |
-
"normalized":
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"unk_token": {
|
| 17 |
-
"content": "
|
| 18 |
"lstrip": false,
|
| 19 |
-
"normalized":
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
|
| 3 |
+
size 587583
|
tokenizer_config.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|