Upload tokenizer

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|pad|>": 50257
+}

special_tokens_map.json

@@ -9,14 +9,14 @@
   "eos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<|pad|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },

tokenizer_config.json

@@ -1,10 +1,19 @@
 {
+  "add_bos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "50256": {
       "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -13,15 +22,9 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
-  "max_length": 512,
+  "errors": "replace",
   "model_max_length": 1024,
-  "pad_to_multiple_of": null,
-  "pad_token": "<|endoftext|>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "stride": 0,
+  "pad_token": "<|pad|>",
   "tokenizer_class": "GPT2Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }