Upload tokenizer
Browse files- special_tokens_map.json +9 -1
- tokenizer.json +9 -0
- tokenizer_config.json +9 -0
special_tokens_map.json
CHANGED
@@ -1 +1,9 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "[EOS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
}
|
9 |
+
}
|
tokenizer.json
CHANGED
@@ -10559,6 +10559,15 @@
|
|
10559 |
"rstrip": false,
|
10560 |
"normalized": false,
|
10561 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10562 |
}
|
10563 |
],
|
10564 |
"normalizer": null,
|
|
|
10559 |
"rstrip": false,
|
10560 |
"normalized": false,
|
10561 |
"special": true
|
10562 |
+
},
|
10563 |
+
{
|
10564 |
+
"id": 10918,
|
10565 |
+
"content": "[EOS]",
|
10566 |
+
"single_word": false,
|
10567 |
+
"lstrip": false,
|
10568 |
+
"rstrip": false,
|
10569 |
+
"normalized": false,
|
10570 |
+
"special": true
|
10571 |
}
|
10572 |
],
|
10573 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -9383,9 +9383,18 @@
|
|
9383 |
"rstrip": false,
|
9384 |
"single_word": false,
|
9385 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9386 |
}
|
9387 |
},
|
9388 |
"clean_up_tokenization_spaces": false,
|
|
|
9389 |
"extra_special_tokens": {},
|
9390 |
"model_max_length": 1024,
|
9391 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
9383 |
"rstrip": false,
|
9384 |
"single_word": false,
|
9385 |
"special": true
|
9386 |
+
},
|
9387 |
+
"10918": {
|
9388 |
+
"content": "[EOS]",
|
9389 |
+
"lstrip": false,
|
9390 |
+
"normalized": false,
|
9391 |
+
"rstrip": false,
|
9392 |
+
"single_word": false,
|
9393 |
+
"special": true
|
9394 |
}
|
9395 |
},
|
9396 |
"clean_up_tokenization_spaces": false,
|
9397 |
+
"eos_token": "[EOS]",
|
9398 |
"extra_special_tokens": {},
|
9399 |
"model_max_length": 1024,
|
9400 |
"tokenizer_class": "PreTrainedTokenizerFast"
|