Upload tokenizer

special_tokens_map.json

@@ -13,6 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_bos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "50256": {
@@ -317,7 +318,9 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "errors": "replace",
   "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
   "return_token_type_ids": false,
   "tokenizer_class": "CodeGenTokenizer",
   "unk_token": "<|endoftext|>"