asahi417 commited on
Commit
7de732a
1 Parent(s): 2c1ed99

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<hl>": 50001
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<hl>"
4
+ ],
5
+ "eos_token": "</s>",
6
+ "pad_token": "<pad>",
7
+ "unk_token": "<unk>"
8
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "eos_token": "</s>",
4
+ "extra_ids": 0,
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "ckpts/mt5-small-zhquad-qag-trimmed-50000",
7
+ "pad_token": "<pad>",
8
+ "sp_model_kwargs": {},
9
+ "special_tokens_map_file": "/home/asahiushio/.cache/huggingface/hub/models--google--mt5-small/snapshots/73fb5dbe4756edadc8fbe8c769b0a109493acf7a/special_tokens_map.json",
10
+ "tokenizer_class": "T5Tokenizer",
11
+ "unk_token": "<unk>"
12
+ }