Commit
·
f308678
1
Parent(s):
634cd34
Upload tokenizer
Browse files- special_tokens_map.json +1 -7
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -13,13 +13,7 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
| 17 |
-
"content": "<unk>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
},
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<unk>",
|
| 25 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -29,7 +29,7 @@
|
|
| 29 |
"clean_up_tokenization_spaces": false,
|
| 30 |
"eos_token": "</s>",
|
| 31 |
"legacy": false,
|
| 32 |
-
"model_max_length":
|
| 33 |
"pad_token": "<unk>",
|
| 34 |
"padding_side": "right",
|
| 35 |
"sp_model_kwargs": {},
|
|
|
|
| 29 |
"clean_up_tokenization_spaces": false,
|
| 30 |
"eos_token": "</s>",
|
| 31 |
"legacy": false,
|
| 32 |
+
"model_max_length": 4096,
|
| 33 |
"pad_token": "<unk>",
|
| 34 |
"padding_side": "right",
|
| 35 |
"sp_model_kwargs": {},
|