Commit
•
df28c6f
1
Parent(s):
e8a0071
Upload tokenizer
Browse files- source.spm +0 -0
- special_tokens_map.json +5 -0
- target.spm +0 -0
- tokenizer_config.json +38 -0
- vocab.json +0 -0
source.spm
ADDED
|
Binary file (834 kB). View file
|
|
|
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 (795 kB). View file
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"44513": {
|
| 4 |
+
"content": "</s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"53367": {
|
| 12 |
+
"content": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"56972": {
|
| 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": "hu",
|
| 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
|
|
|