Upload tokenizer

special_tokens_map.json

@@ -1,19 +1,7 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "<sos>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<eos>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "<sos>",
+    "<eos>"
   ],
   "bos_token": {
     "content": "<|endoftext|>",
@@ -29,7 +17,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer_config.json

@@ -41,12 +41,16 @@
     "<eos>"
   ],
   "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
+  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "<|endoftext|>",
   "padding_side": "right",
+  "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }