Nettem-Gayathri
commited on
Commit
•
865a2a0
1
Parent(s):
634536e
Upload tokenizer
Browse files- .gitattributes +1 -0
- README.md +1 -1
- source.spm +3 -0
- special_tokens_map.json +5 -0
- target.spm +0 -0
- tokenizer_config.json +38 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
source.spm filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: Helsinki-NLP/opus-mt-hi-en
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
|
|
6 |
model-index:
|
7 |
- name: HI-EN-translation
|
8 |
results: []
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
3 |
tags:
|
4 |
- generated_from_keras_callback
|
5 |
+
base_model: Helsinki-NLP/opus-mt-hi-en
|
6 |
model-index:
|
7 |
- name: HI-EN-translation
|
8 |
results: []
|
source.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd20c408ec4568361d32b41080e3f6fa5b82895135bd25c2747b2c145e42d07b
|
3 |
+
size 1057690
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
target.spm
ADDED
Binary file (813 kB). View file
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "</s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<unk>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"61126": {
|
20 |
+
"content": "<pad>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"clean_up_tokenization_spaces": true,
|
29 |
+
"eos_token": "</s>",
|
30 |
+
"model_max_length": 512,
|
31 |
+
"pad_token": "<pad>",
|
32 |
+
"separate_vocabs": false,
|
33 |
+
"source_lang": "hi",
|
34 |
+
"sp_model_kwargs": {},
|
35 |
+
"target_lang": "en",
|
36 |
+
"tokenizer_class": "MarianTokenizer",
|
37 |
+
"unk_token": "<unk>"
|
38 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|