add tokenizer
Browse files- .gitattributes +2 -0
- source.spm +3 -0
- special_tokens_map.json +1 -0
- target.spm +3 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
source.spm filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
target.spm filter=lfs diff=lfs merge=lfs -text
|
source.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a6356e3ee892f2896dbf0b5cabeb51fdf16e03c70b0702cefc8b847e504241c
|
| 3 |
+
size 839750
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
target.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cc15427e50b80e53b7dcf5f4d8a52edfe219b8d8e290c031f5578f5760b335f
|
| 3 |
+
size 796647
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"source_lang": "tr", "target_lang": "en", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "separate_vocabs": false, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "tr_en-Academic_translation", "tokenizer_class": "MarianTokenizer"}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|