Upload tokenizer
Browse files- special_tokens_map.json +5 -0
- spiece.model +3 -0
- tokenizer_config.json +14 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "</s>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c65feffa65ff0378759778193852083d23349cb1b40c906e9463a12f8076ff32
|
| 3 |
+
size 680811
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [],
|
| 3 |
+
"do_lower_case": true,
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"extra_ids": 0,
|
| 6 |
+
"max_length": 1024,
|
| 7 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"pad_token": "<pad>",
|
| 9 |
+
"sp_model_kwargs": {},
|
| 10 |
+
"special_tokens_map_file": "/cognitive_comp/wuxiaojun/pretrained/pytorch/Randeng-T5-784M/special_tokens_map.json",
|
| 11 |
+
"tokenizer_class": "T5Tokenizer",
|
| 12 |
+
"truncation": true,
|
| 13 |
+
"unk_token": "<unk>"
|
| 14 |
+
}
|