Upload tokenizer
Browse files- special_tokens_map.json +4 -4
- tokenizer_config.json +20 -0
special_tokens_map.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": "
|
| 3 |
-
"eos_token": "
|
| 4 |
-
"pad_token": "
|
| 5 |
-
"unk_token": "
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "[PAD]",
|
| 3 |
+
"eos_token": "[PAD]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"unk_token": "[UNK]"
|
| 6 |
}
|
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,27 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"clean_up_tokenization_spaces": false,
|
| 3 |
"do_lower_case": false,
|
| 4 |
"do_normalize": false,
|
|
|
|
| 5 |
"extra_special_tokens": {},
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
"pad_token": "[PAD]",
|
|
|
|
| 1 |
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
}
|
| 19 |
+
},
|
| 20 |
+
"bos_token": "[PAD]",
|
| 21 |
"clean_up_tokenization_spaces": false,
|
| 22 |
"do_lower_case": false,
|
| 23 |
"do_normalize": false,
|
| 24 |
+
"eos_token": "[PAD]",
|
| 25 |
"extra_special_tokens": {},
|
| 26 |
"model_max_length": 1000000000000000019884624838656,
|
| 27 |
"pad_token": "[PAD]",
|