Marko Tasic
commited on
Commit
•
76966fb
1
Parent(s):
e8e7cb3
tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +5 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
- vocab.json +0 -0
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|begin_of_text|>",
|
| 3 |
+
"eos_token": "<|end_of_text|>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de12352815a18902973a43e535c747ddad999c72675e43002972892f1903cf75
|
| 3 |
+
size 2113290
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|