Commit
·
5d2bc4e
1
Parent(s):
081f1e4
Upload tokenizer
Browse files- special_tokens_map.json +21 -9
- tokenizer_config.json +1 -6
special_tokens_map.json
CHANGED
|
@@ -1,11 +1,23 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"<
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
"
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
}
|
tokenizer_config.json
CHANGED
|
@@ -25,17 +25,12 @@
|
|
| 25 |
"special": true
|
| 26 |
}
|
| 27 |
},
|
| 28 |
-
"additional_special_tokens": [
|
| 29 |
-
"<unk>",
|
| 30 |
-
"<s>",
|
| 31 |
-
"</s>"
|
| 32 |
-
],
|
| 33 |
"bos_token": "<s>",
|
| 34 |
"clean_up_tokenization_spaces": false,
|
| 35 |
"eos_token": "</s>",
|
| 36 |
"legacy": false,
|
| 37 |
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
-
"pad_token":
|
| 39 |
"padding_side": "right",
|
| 40 |
"return_token_type_ids": false,
|
| 41 |
"sp_model_kwargs": {},
|
|
|
|
| 25 |
"special": true
|
| 26 |
}
|
| 27 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
"bos_token": "<s>",
|
| 29 |
"clean_up_tokenization_spaces": false,
|
| 30 |
"eos_token": "</s>",
|
| 31 |
"legacy": false,
|
| 32 |
"model_max_length": 1000000000000000019884624838656,
|
| 33 |
+
"pad_token": null,
|
| 34 |
"padding_side": "right",
|
| 35 |
"return_token_type_ids": false,
|
| 36 |
"sp_model_kwargs": {},
|