add tokenizer
Browse files- .gitattributes +1 -0
- special_tokens_map.json +7 -0
- tokenizer.json +3 -0
- tokenizer_config.json +5 -0
.gitattributes
CHANGED
@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
30 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
31 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
32 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
30 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
31 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
32 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
33 |
+
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:d3bc9f61f664c813966468bbae2727ab217a30c71a303b2901c409f8daf632b4
|
3 |
+
size 1049435
|
tokenizer_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"name_or_path": "gogamza/kobart-base-v2",
|
3 |
+
"special_tokens_map_file": "/home/circulus/.cache/huggingface/transformers/a87d2ed77831bb40ce806a97c04126addf5ecc82b3e23ecf916b2a4acdb9c29a.c23d5e62137984cf842a885705037b25b156747d145406702932d5f5d5e7c88e",
|
4 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
5 |
+
}
|