Upload tokenizer
Browse files- tokenizer.json +1 -0
- tokenizer_config.json +1 -2
tokenizer.json
CHANGED
@@ -2103,6 +2103,7 @@
|
|
2103 |
"continuing_subword_prefix": null,
|
2104 |
"end_of_word_suffix": null,
|
2105 |
"fuse_unk": false,
|
|
|
2106 |
"vocab": {
|
2107 |
"<s>": 0,
|
2108 |
"</s>": 1,
|
|
|
2103 |
"continuing_subword_prefix": null,
|
2104 |
"end_of_word_suffix": null,
|
2105 |
"fuse_unk": false,
|
2106 |
+
"byte_fallback": false,
|
2107 |
"vocab": {
|
2108 |
"<s>": 0,
|
2109 |
"</s>": 1,
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"model_max_length": 1000000000000000019884624838656,
|
3 |
-
"name_or_path": "gogamza/kobart-base-v2",
|
4 |
-
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--gogamza--kobart-base-v2/snapshots/f9f2ec35d3c32a1ecc7a3281f9626b7ec1913fed/special_tokens_map.json",
|
5 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
|
4 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
5 |
}
|