add tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<|endoftext|>"]}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": false, "unk_token": "<unk>", "pad_token": "<pad>", "bos_token": "<s>", "eos_token": "</s>", "special_tokens_map_file": "/home/conversational_model/kobart/special_tokens_map.json", "name_or_path": "/home/conversational_model/kobart", "tokenizer_class": "PreTrainedTokenizerFast"}
|