Upload tokenizer

special_tokens_map.json

@@ -12,5 +12,12 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
   }
 }

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_bos_token": true,
   "added_tokens_decoder": {
     "128000": {
       "content": "<|begin_of_text|>",
@@ -2059,5 +2060,8 @@
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "tokenizer_class": "PreTrainedTokenizer"
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "left",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
 }