Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"cls_token": "[CLS]",
|
| 6 |
+
"is_local": true,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"max_length": 1024,
|
| 9 |
+
"model_input_names": [
|
| 10 |
+
"input_ids",
|
| 11 |
+
"attention_mask"
|
| 12 |
+
],
|
| 13 |
+
"model_max_length": 8192,
|
| 14 |
+
"pad_token": "[PAD]",
|
| 15 |
+
"sep_token": "[SEP]",
|
| 16 |
+
"stride": 0,
|
| 17 |
+
"tokenizer_class": "TokenizersBackend",
|
| 18 |
+
"truncation_side": "right",
|
| 19 |
+
"truncation_strategy": "longest_first",
|
| 20 |
+
"unk_token": "[UNK]"
|
| 21 |
+
}
|