Upload tokenizer
Browse files- tokenizer.json +1 -0
- tokenizer_config.json +2 -2
tokenizer.json
CHANGED
@@ -2098,6 +2098,7 @@
|
|
2098 |
"continuing_subword_prefix": null,
|
2099 |
"end_of_word_suffix": null,
|
2100 |
"fuse_unk": false,
|
|
|
2101 |
"vocab": {
|
2102 |
"<s>": 0,
|
2103 |
"</s>": 1,
|
|
|
2098 |
"continuing_subword_prefix": null,
|
2099 |
"end_of_word_suffix": null,
|
2100 |
"fuse_unk": false,
|
2101 |
+
"byte_fallback": false,
|
2102 |
"vocab": {
|
2103 |
"<s>": 0,
|
2104 |
"</s>": 1,
|
tokenizer_config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
5 |
}
|
|
|
1 |
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"model_max_length": 1000000000000000019884624838656,
|
4 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
5 |
}
|