Upload tokenizer
Browse files- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [],
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_lower_case": true,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"extra_ids": 0,
|
| 8 |
+
"mask_token": "[MASK]",
|
| 9 |
+
"name_or_path": "/content/output",
|
| 10 |
+
"pad_token": "[PAD]",
|
| 11 |
+
"sep_token": "[SEP]",
|
| 12 |
+
"sp_model_kwargs": {},
|
| 13 |
+
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--rinna--japanese-gpt2-medium/snapshots/16d2b5ac6442ca11562fb92a683f2e421fd9056f/special_tokens_map.json",
|
| 14 |
+
"tokenizer_class": "T5Tokenizer",
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|