Upload tokenizer
Browse files- added_tokens.json +4 -0
- special_tokens_map.json +11 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<mask>": 40001,
|
3 |
+
"<pad>": 40000
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>",
|
4 |
+
"<mask>"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"eos_token": "</s>",
|
8 |
+
"mask_token": "<mask>",
|
9 |
+
"pad_token": "<pad>",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a1836aa16c5e41fb9bec14c477218b83812919d19dfdde1c49a419cd9935615
|
3 |
+
size 858518
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>",
|
4 |
+
"<mask>"
|
5 |
+
],
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"extra_ids": 0,
|
8 |
+
"name_or_path": "drive/MyDrive/Models/t5-base-answer-to-query-generation-v20221018/checkpoint-90000",
|
9 |
+
"pad_token": "<pad>",
|
10 |
+
"sp_model_kwargs": {},
|
11 |
+
"special_tokens_map_file": "/cognitive_comp/gaoxinyu/hf_hub/Randeng-BART-139M/special_tokens_map.json",
|
12 |
+
"tokenizer_class": "T5Tokenizer",
|
13 |
+
"unk_token": "<unk>"
|
14 |
+
}
|