itwk commited on
Commit
4ee5415
·
verified ·
1 Parent(s): 1210646

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 sha256:8dae8bae9e4260b92870b8cabac37d29da43c5ee01054dbc65e83486a8506cb1
3
+ size 98410
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 12126.000000 12126.000000 12126.000000
3
+ mean 67.715405 137.806037 0.496522
4
+ std 62.596447 128.612045 0.042998
5
+ min 16.000000 41.000000 0.346939
6
+ 10% 25.000000 50.000000 0.451923
7
+ 25% 32.000000 63.000000 0.470056
8
+ 33% 36.000000 72.000000 0.476923
9
+ 50% 48.000000 98.000000 0.490909
10
+ 67% 66.000000 135.000000 0.506391
11
+ 75% 79.000000 161.000000 0.515152
12
+ 80% 90.000000 186.000000 0.521739
13
+ 90% 129.000000 267.000000 0.543210
14
+ 95% 177.000000 363.750000 0.569576
15
+ 99% 314.000000 653.000000 0.652990
16
+ max 1045.000000 2255.000000 0.918367
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
+ "6000": {
20
+ "content": "<0x{i:02X}>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "6001": {
28
+ "content": "…",
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
+ }