Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "<|startoftext|>": 50258,
-  "[PAD]": 50257
+  "<|startoftext|>": 53082,
+  "[PAD]": 53081
 }

special_tokens_map.json

@@ -2,5 +2,11 @@
   "bos_token": "<|startoftext|>",
   "eos_token": "<|endoftext|>",
   "pad_token": "[PAD]",
-  "unk_token": "<|endoftext|>"
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,9 +1,33 @@
 {
+  "add_bos_token": false,
   "add_prefix_space": false,
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 1024,
-  "special_tokens_map_file": null,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "special_tokens_map_file": "tokenizer_folder/new_tokenizer_gpt\\special_tokens_map.json",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }