Upload tokenizer

special_tokens_map.json

@@ -35,9 +35,9 @@
     "single_word": false
   },
   "sep_token": {
-    "content": "</s>",
+    "content": "<|end|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },

tokenizer.json

@@ -3,6 +3,15 @@
   "truncation": null,
   "padding": null,
   "added_tokens": [
+    {
+      "id": 2,
+      "content": "<|end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
     {
       "id": 3,
       "content": "<|user|>",

tokenizer_config.json

@@ -1,6 +1,14 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
+    "2": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
     "3": {
       "content": "<|user|>",
       "lstrip": false,
@@ -74,7 +82,7 @@
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "sep_token": "</s>",
+  "sep_token": "<|end|>",
   "tokenizer_class": "RobertaTokenizer",
   "trim_offsets": true,
   "unk_token": "<unk>"