Upload tokenizer

added_tokens.json

@@ -1,3 +1,3 @@
 {
-  "1": 1
+  "1 ": 1
 }

special_tokens_map.json

@@ -1,4 +1,4 @@
 {
-  "bos_token": "0",
-  "eos_token": "1"
+  "bos_token": "0 ",
+  "eos_token": "1 "
 }

tokenizer.json

@@ -5,7 +5,7 @@
   "added_tokens": [
     {
       "id": 0,
-      "content": "0",
+      "content": "0 ",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -14,7 +14,7 @@
     },
     {
       "id": 1,
-      "content": "1",
+      "content": "1 ",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -51,7 +51,7 @@
     "byte_fallback": false,
     "ignore_merges": false,
     "vocab": {
-      "0": 0
+      "0 ": 0
     },
     "merges": []
   }

tokenizer_config.json

@@ -2,7 +2,7 @@
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "0",
+      "content": "0 ",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -10,7 +10,7 @@
       "special": true
     },
     "1": {
-      "content": "1",
+      "content": "1 ",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -18,9 +18,9 @@
       "special": true
     }
   },
-  "bos_token": "0",
+  "bos_token": "0 ",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "1",
+  "eos_token": "1 ",
   "model_max_length": 1000000000000000019884624838656,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": ""

vocab.json

@@ -1 +1 @@
-{"0":0}
+{"0 ":0}