Upload tokenizer

special_tokens_map.json

@@ -1,4 +1,8 @@
 {
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
   "bos_token": {
     "content": "<|beginoftext|>",
     "lstrip": false,

tokenizer.json

@@ -23,7 +23,7 @@
     },
     {
       "id": 2,
-      "content": "<|reserved_token_1|>",
+      "content": "<|im_start|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -32,7 +32,7 @@
     },
     {
       "id": 3,
-      "content": "<|reserved_token_2|>",
+      "content": "<|im_end|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -215,8 +215,8 @@
     "vocab": {
       "<|endoftext|>": 0,
       "<|beginoftext|>": 1,
-      "<|reserved_token_1|>": 2,
-      "<|reserved_token_2|>": 3,
+      "<|im_start|>": 2,
+      "<|im_end|>": 3,
       "<|reserved_token_3|>": 4,
       "<|reserved_token_4|>": 5,
       "<|reserved_token_5|>": 6,

tokenizer_config.json

@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "<|reserved_token_1|>",
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,7 +25,7 @@
       "special": true
     },
     "3": {
-      "content": "<|reserved_token_2|>",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -105,7 +105,12 @@
       "special": true
     }
   },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
   "bos_token": "<|beginoftext|>",
+  "chat_template": "{% for message in messages %}{% if message.get('role') is not none %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% else %}{{message['content'] + '<|im_end|>' + '\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},