Delete tokenizer
Browse files- tokenizer/source.spm +0 -0
- tokenizer/special_tokens_map.json +0 -5
- tokenizer/target.spm +0 -0
- tokenizer/tokenizer_config.json +0 -38
- tokenizer/vocab.json +0 -0
tokenizer/source.spm
DELETED
|
Binary file (797 kB)
|
|
|
tokenizer/special_tokens_map.json
DELETED
|
@@ -1,5 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"eos_token": "</s>",
|
| 3 |
-
"pad_token": "<pad>",
|
| 4 |
-
"unk_token": "<unk>"
|
| 5 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer/target.spm
DELETED
|
Binary file (823 kB)
|
|
|
tokenizer/tokenizer_config.json
DELETED
|
@@ -1,38 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"added_tokens_decoder": {
|
| 3 |
-
"42432": {
|
| 4 |
-
"content": "</s>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"51366": {
|
| 12 |
-
"content": "<unk>",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"57702": {
|
| 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": "en",
|
| 34 |
-
"sp_model_kwargs": {},
|
| 35 |
-
"target_lang": "ces+slk",
|
| 36 |
-
"tokenizer_class": "MarianTokenizer",
|
| 37 |
-
"unk_token": "<unk>"
|
| 38 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|