Upload tokenizer

added_tokens.json

@@ -1,5 +1,6 @@
 {
-  "<|assistant|>": 50258,
+  "<|assistant|>": 50260,
   "<|end|>": 50259,
+  "<|system|>": 50258,
   "<|user|>": 50257
 }

special_tokens_map.json

@@ -8,7 +8,7 @@
       "single_word": false
     },
     {
-      "content": "<|assistant|>",
+      "content": "<|system|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -20,6 +20,13 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false
+    },
+    {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
     }
   ],
   "bos_token": "<|endoftext|>",

tokenizer.json

@@ -23,7 +23,7 @@
     },
     {
       "id": 50258,
-      "content": "<|assistant|>",
+      "content": "<|system|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -38,6 +38,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 50260,
+      "content": "<|assistant|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -18,7 +18,7 @@
       "special": true
     },
     "50258": {
-      "content": "<|assistant|>",
+      "content": "<|system|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -32,14 +32,24 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "50260": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
     "<|user|>",
-    "<|assistant|>",
-    "<|end|>"
+    "<|system|>",
+    "<|end|>",
+    "<|assistant|>"
   ],
   "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|endoftext|><|user|>\n' + message['content'] + '<|end|>\n' }}{% elif message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '<|end|>\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>\n' + message['content'] + '<|end|><|endoftext|>\n' }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,