Xenova HF staff commited on
Commit
d2fd093
1 Parent(s): 5b92e4b

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +23 -0
  2. spiece.model +3 -0
  3. tokenizer_config.json +33 -0
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": true,
5
+ "normalized": false,
6
+ "rstrip": true,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "</s>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": true,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ }
23
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e5036bed065526c3c212dfbe288752391797c4bb1a284aa18c9a0b23fcaf8ec
3
+ size 798330
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "1": {
4
+ "content": "</s>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "2": {
12
+ "content": "<unk>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": true
18
+ }
19
+ },
20
+ "additional_special_tokens": [],
21
+ "clean_up_tokenization_spaces": true,
22
+ "do_lower_case": true,
23
+ "eos_token": "</s>",
24
+ "model_input_names": [
25
+ "input_ids"
26
+ ],
27
+ "model_max_length": 64,
28
+ "pad_token": "</s>",
29
+ "processor_class": "SiglipProcessor",
30
+ "sp_model_kwargs": {},
31
+ "tokenizer_class": "SiglipTokenizer",
32
+ "unk_token": "<unk>"
33
+ }