Upload tokenizer

special_tokens_map.json

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

tokenizer.json

@@ -71,6 +71,12 @@
           "id": "A",
           "type_id": 0
         }
+      },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
       }
     ],
     "pair": [
@@ -86,6 +92,12 @@
           "type_id": 0
         }
       },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
+      },
       {
         "SpecialToken": {
           "id": "<s>",
@@ -97,9 +109,24 @@
           "id": "B",
           "type_id": 1
         }
+      },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 1
+        }
       }
     ],
     "special_tokens": {
+      "</s>": {
+        "id": "</s>",
+        "ids": [
+          2
+        ],
+        "tokens": [
+          "</s>"
+        ]
+      },
       "<s>": {
         "id": "<s>",
         "ids": [

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "add_bos_token": true,
-  "add_eos_token": false,
+  "add_eos_token": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -39,8 +39,10 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,
+  "max_lenght": 2048,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<unk>",
+  "pad_token": "</s>",
+  "padding": true,
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",