itwk commited on
Commit
c31f2ff
·
verified ·
1 Parent(s): f05fa32

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:b2b2df59c8a5a80018e7668b7ddb4a4845ec7434735e463b95b32c8c6ee31f0c
3
+ size 91529
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 9629.000000 9629.000000 9629.000000
3
+ mean 169.377713 308.383217 0.559246
4
+ std 132.259611 240.259677 0.081961
5
+ min 14.000000 41.000000 0.311111
6
+ 10% 36.000000 54.000000 0.480754
7
+ 25% 66.000000 124.000000 0.508065
8
+ 33% 90.000000 167.000000 0.519366
9
+ 50% 139.000000 257.000000 0.543478
10
+ 67% 197.000000 361.000000 0.570467
11
+ 75% 233.000000 425.000000 0.586957
12
+ 80% 259.000000 472.000000 0.600613
13
+ 90% 343.000000 622.000000 0.650367
14
+ 95% 430.000000 769.000000 0.788077
15
+ 99% 602.000000 1121.760000 0.820000
16
+ max 1045.000000 1856.000000 0.840909
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
+ }