Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +5 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"mask_token": "<mask>",
|
5 |
+
"pad_token": "</s>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"name_or_path": "./Models/dialoGPT-base-korean-chit-chat-v2/save-checkpoint-180000/checkpoint-12000",
|
3 |
+
"special_tokens_map_file": "../base_model/kogpt2-base-v2/special_tokens_map.json",
|
4 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
5 |
+
}
|