Upload tokenizer
Browse files- .gitattributes +1 -0
- special_tokens_map.json +24 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
|
@@ -38,3 +38,4 @@ checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 38 |
checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 38 |
checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f164843d225ed4edbde885a9181e435046b7380a37410962a40c3a6c79b9a7c
|
| 3 |
+
size 17078387
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|