bdunnette commited on
Commit
b2adf3d
1 Parent(s): 6ef0a5a

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +89 -0
  2. special_tokens_map.json +3 -13
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +6 -44
  5. vocab.json +0 -0
merges.txt CHANGED
@@ -24742,3 +24742,92 @@ Harm ac
24742
  Pan ter
24743
  Pan ama
24744
  Ray n
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24742
  Pan ter
24743
  Pan ama
24744
  Ray n
24745
+ Ray kee
24746
+ Tam er
24747
+ ĠBell ion
24748
+ ĠBell ringer
24749
+ cho Cinco
24750
+ As ia
24751
+ As alt
24752
+ As aulty
24753
+ As phyxi
24754
+ Cry Baby
24755
+ Cry pt
24756
+ Cry pto
24757
+ Jun ior
24758
+ Ly ric
24759
+ Ly ssa
24760
+ Ly kr
24761
+ Mort ar
24762
+ Mort is
24763
+ Mayhem s
24764
+ Pand oras
24765
+ Sand storm
24766
+ isty k
24767
+ ĠLo athe
24768
+ Scrap e
24769
+ Scrap per
24770
+ Scrap pers
24771
+ Day a
24772
+ Day zee
24773
+ Day tona
24774
+ Pl ower
24775
+ UR His
24776
+ Ġla ya
24777
+ isk atrix
24778
+ isk ated
24779
+ ĠDod g
24780
+ ors et
24781
+ ĠLu cha
24782
+ ĠAw kward
24783
+ ĠWitch y
24784
+ Ali as
24785
+ Bell ona
24786
+ Bell istic
24787
+ On na
24788
+ On Ya
24789
+ Riot er
24790
+ Tar en
24791
+ Tar ah
24792
+ to es
24793
+ ĠMay o
24794
+ ĠMay ham
24795
+ ĠMay onnaise
24796
+ ĠDemon ium
24797
+ ĠEd ee
24798
+ ĠEd dy
24799
+ ĠEd ges
24800
+ ĠEd usk
24801
+ ĠKnox xx
24802
+ Mega Bite
24803
+ Ber i
24804
+ Ber ri
24805
+ Count em
24806
+ Count essa
24807
+ Fre enia
24808
+ Hal a
24809
+ Op al
24810
+ Sher e
24811
+ Sher ri
24812
+ Sher man
24813
+ Sher yl
24814
+ ĠDer rière
24815
+ heart less
24816
+ ĠStomp Her
24817
+ ĠStomp sky
24818
+ Ana is
24819
+ Short Stack
24820
+ opp osition
24821
+ ĠSkull en
24822
+ ĠSkull Shiner
24823
+ ĠSkull Krusher
24824
+ Slaughter mel
24825
+ Goldie Lock
24826
+ Bra un
24827
+ Bra kes
24828
+ Bra ids
24829
+ Can uk
24830
+ Can uckle
24831
+ Cam reon
24832
+ Crack lin
24833
+ Crack alack
special_tokens_map.json CHANGED
@@ -1,15 +1,5 @@
1
  {
2
- "bos_token": "[CLS]",
3
- "cls_token": "[CLS]",
4
- "eos_token": "[SEP]",
5
- "mask_token": {
6
- "content": "[MASK]",
7
- "lstrip": true,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "pad_token": "<pad>",
13
- "sep_token": "[SEP]",
14
- "unk_token": "<unk>"
15
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
5
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,57 +1,19 @@
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "[CLS]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
- },
11
- "1": {
12
- "content": "[SEP]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "<unk>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "<pad>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "[MASK]",
37
- "lstrip": true,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
  }
43
  },
44
- "bos_token": "[CLS]",
45
  "clean_up_tokenization_spaces": false,
46
- "cls_token": "[CLS]",
47
- "do_lower_case": true,
48
- "eos_token": "[SEP]",
49
- "keep_accents": false,
50
- "mask_token": "[MASK]",
51
  "model_max_length": 1000000000000000019884624838656,
52
- "pad_token": "<pad>",
53
- "remove_space": true,
54
- "sep_token": "[SEP]",
55
- "tokenizer_class": "AlbertTokenizer",
56
- "unk_token": "<unk>"
57
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
+ "content": "<|endoftext|>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  }
12
  },
13
+ "bos_token": "<|endoftext|>",
14
  "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
 
 
 
 
16
  "model_max_length": 1000000000000000019884624838656,
17
+ "tokenizer_class": "GPT2Tokenizer",
18
+ "unk_token": "<|endoftext|>"
 
 
 
19
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff