Upload tokenizer

special_tokens_map.json

@@ -14,7 +14,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "</s>",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -62,6 +62,12 @@
           "id": "A",
           "type_id": 0
         }
+      },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
       }
     ],
     "pair": [
@@ -77,6 +83,12 @@
           "type_id": 0
         }
       },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
+      },
       {
         "SpecialToken": {
           "id": "<s>",
@@ -88,9 +100,24 @@
           "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 +1,7 @@
 {
   "add_bos_token": true,
-  "add_eos_token": false,
+  "add_eos_token": true,
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -33,9 +34,10 @@
   "eos_token": "</s>",
   "legacy": false,
   "model_max_length": 2048,
-  "pad_token": "</s>",
+  "pad_token": "<unk>",
   "padding_side": "right",
   "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false