Upload tokenizer

merges.txt

@@ -24742,3 +24742,92 @@ Harm ac
 Pan ter
 Pan ama
 Ray n
+Ray kee
+Tam er
+ĠBell ion
+ĠBell ringer
+cho Cinco
+As ia
+As alt
+As aulty
+As phyxi
+Cry Baby
+Cry pt
+Cry pto
+Jun ior
+Ly ric
+Ly ssa
+Ly kr
+Mort ar
+Mort is
+Mayhem s
+Pand oras
+Sand storm
+isty k
+ĠLo athe
+Scrap e
+Scrap per
+Scrap pers
+Day a
+Day zee
+Day tona
+Pl ower
+UR His
+Ġla ya
+isk atrix
+isk ated
+ĠDod g
+ors et
+ĠLu cha
+ĠAw kward
+ĠWitch y
+Ali as
+Bell ona
+Bell istic
+On na
+On Ya
+Riot er
+Tar en
+Tar ah
+to es
+ĠMay o
+ĠMay ham
+ĠMay onnaise
+ĠDemon ium
+ĠEd ee
+ĠEd dy
+ĠEd ges
+ĠEd usk
+ĠKnox xx
+Mega Bite
+Ber i
+Ber ri
+Count em
+Count essa
+Fre enia
+Hal a
+Op al
+Sher e
+Sher ri
+Sher man
+Sher yl
+ĠDer rière
+heart less
+ĠStomp Her
+ĠStomp sky
+Ana is
+Short Stack
+opp osition
+ĠSkull en
+ĠSkull Shiner
+ĠSkull Krusher
+Slaughter mel
+Goldie Lock
+Bra un
+Bra kes
+Bra ids
+Can uk
+Can uckle
+Cam reon
+Crack lin
+Crack alack

special_tokens_map.json

@@ -1,15 +1,5 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "[SEP]",
-  "unk_token": "<unk>"
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -1,57 +1,19 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "[CLS]",
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "1": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "[MASK]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "bos_token": "[CLS]",
+  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "eos_token": "[SEP]",
-  "keep_accents": false,
-  "mask_token": "[MASK]",
+  "eos_token": "<|endoftext|>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "remove_space": true,
-  "sep_token": "[SEP]",
-  "tokenizer_class": "AlbertTokenizer",
-  "unk_token": "<unk>"
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
 }