itwk commited on
Commit
5f7cb47
·
verified ·
1 Parent(s): 1b07d95

Upload 7 files

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "mask_token": "…",
4
+ "unk_token": "<unk>"
5
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ecc65941f493a05bc362d7323629db1120616302da28e07a46d25804620d8cc
3
+ size 92567
spiece.vocab ADDED
The diff for this file is too large to render. See raw diff
 
token_fraction.csv ADDED
The diff for this file is too large to render. See raw diff
 
token_fraction_describe.txt ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ token text token/text
2
+ count 23330.000000 23330.000000 23330.000000
3
+ mean 130.110502 247.216974 0.536266
4
+ std 136.326241 256.746274 0.086492
5
+ min 14.000000 41.000000 0.288462
6
+ 10% 28.000000 51.000000 0.450000
7
+ 25% 39.000000 70.000000 0.479899
8
+ 33% 47.000000 84.000000 0.492537
9
+ 50% 88.000000 172.000000 0.519231
10
+ 67% 148.000000 285.000000 0.550117
11
+ 75% 183.000000 351.000000 0.569572
12
+ 80% 211.000000 404.000000 0.586957
13
+ 90% 293.000000 555.000000 0.645841
14
+ 95% 368.000000 699.000000 0.725490
15
+ 99% 541.710000 1009.710000 0.795455
16
+ max 9957.000000 18459.000000 1.047619
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "904": {
20
+ "content": "…",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "6000": {
28
+ "content": "<0x{i:02X}>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "clean_up_tokenization_spaces": true,
37
+ "eos_token": "</s>",
38
+ "mask_token": "…",
39
+ "model_max_length": 1000000000000000019884624838656,
40
+ "tokenizer_class": "PreTrainedTokenizerFast",
41
+ "unk_token": "<unk>"
42
+ }