Upload tokenizer

added_tokens.json

@@ -1,4 +1,3 @@
 {
-  "<pad>": 32000,
-  "[PAD]": 32001
+  "<pad>": 32000
 }

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -43,15 +43,6 @@
       "rstrip": false,
       "normalized": true,
       "special": false
-    },
-    {
-      "id": 32001,
-      "content": "[PAD]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -33,14 +33,6 @@
       "rstrip": false,
       "single_word": false,
       "special": false
-    },
-    "32001": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<s>",
@@ -48,7 +40,7 @@
   "eos_token": "</s>",
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "pad_token": "<unk>",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",