Upload tokenizer
Browse files- special_tokens_map.json +9 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +25 -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 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5cbdfa8aa7c54c8c5af85b78c309c54a5f2749a20468bf6f60eee007fe6fec1
|
| 3 |
+
size 805634
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [],
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"cls_token": "[CLS]",
|
| 6 |
+
"do_lower_case": true,
|
| 7 |
+
"eos_token": "</s>",
|
| 8 |
+
"extra_ids": 0,
|
| 9 |
+
"is_fast": true,
|
| 10 |
+
"legacy": true,
|
| 11 |
+
"mask_token": "[MASK]",
|
| 12 |
+
"max_length": 384,
|
| 13 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_token": "[PAD]",
|
| 16 |
+
"pad_token_type_id": 0,
|
| 17 |
+
"padding_side": "right",
|
| 18 |
+
"sep_token": "[SEP]",
|
| 19 |
+
"sp_model_kwargs": {},
|
| 20 |
+
"stride": 0,
|
| 21 |
+
"tokenizer_class": "T5Tokenizer",
|
| 22 |
+
"truncation_side": "right",
|
| 23 |
+
"truncation_strategy": "only_second",
|
| 24 |
+
"unk_token": "<unk>"
|
| 25 |
+
}
|