add tokenizer
Browse files- .gitattributes +1 -0
- special_tokens_map.json +7 -0
- tokenizer.json +3 -0
- tokenizer_config.json +8 -0
.gitattributes
CHANGED
|
@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 30 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 30 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"mask_token": "<mask>",
|
| 5 |
+
"pad_token": "<pad>",
|
| 6 |
+
"unk_token": "<unk>"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:444f68abc3b798ce3f285f1afff88f634a15514d53c11b49d5f9f640a006af03
|
| 3 |
+
size 1049337
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"mask_token": "<mask>",
|
| 5 |
+
"pad_token": "<pad>",
|
| 6 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 7 |
+
"unk_token": "<unk>"
|
| 8 |
+
}
|