Update tokenizer_config.json
Browse files- tokenizer_config.json +13 -33
tokenizer_config.json
CHANGED
|
@@ -1,37 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
-
"0": {
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"1": {
|
| 12 |
-
"content": "[BOS]",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "[EOS]",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
-
"content": "[UNK]",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
}
|
| 35 |
},
|
| 36 |
"bos_token": "[BOS]",
|
| 37 |
"clean_up_tokenization_spaces": false,
|
|
@@ -40,5 +12,13 @@
|
|
| 40 |
"model_max_length": 1000000000000000019884624838656,
|
| 41 |
"pad_token": "[PAD]",
|
| 42 |
"tokenizer_class": "SquaresOnlyChessTokenizer",
|
| 43 |
-
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
+
"0": {"content":"[PAD]","lstrip":false,"normalized":false,"rstrip":false,"single_word":false,"special":true},
|
| 4 |
+
"1": {"content":"[BOS]","lstrip":false,"normalized":false,"rstrip":false,"single_word":false,"special":true},
|
| 5 |
+
"2": {"content":"[EOS]","lstrip":false,"normalized":false,"rstrip":false,"single_word":false,"special":true},
|
| 6 |
+
"3": {"content":"[UNK]","lstrip":false,"normalized":false,"rstrip":false,"single_word":false,"special":true}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
},
|
| 8 |
"bos_token": "[BOS]",
|
| 9 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 12 |
"model_max_length": 1000000000000000019884624838656,
|
| 13 |
"pad_token": "[PAD]",
|
| 14 |
"tokenizer_class": "SquaresOnlyChessTokenizer",
|
| 15 |
+
"unk_token": "[UNK]",
|
| 16 |
+
|
| 17 |
+
"use_fast": false,
|
| 18 |
+
"auto_map": {
|
| 19 |
+
"AutoTokenizer": [
|
| 20 |
+
"tokenizer.SquaresOnlyChessTokenizer",
|
| 21 |
+
null
|
| 22 |
+
]
|
| 23 |
+
}
|
| 24 |
}
|