Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|pad|>": 50258,
+  "<|startoftext|>": 50257
+}

special_tokens_map.json

@@ -1,5 +1,24 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": "<|endoftext|>"
 }

tokenizer.json

@@ -11,6 +11,24 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 50257,
+      "content": "<|startoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true,
+      "special": true
+    },
+    {
+      "id": 50258,
+      "content": "<|pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -3,7 +3,7 @@
   "add_prefix_space": false,
   "bos_token": {
     "__type": "AddedToken",
-    "content": "<|endoftext|>",
+    "content": "<|startoftext|>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
@@ -20,7 +20,14 @@
   },
   "errors": "replace",
   "model_max_length": 2048,
-  "pad_token": null,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": {
     "__type": "AddedToken",