Upload tokenizer

chat_template.jinja

@@ -0,0 +1,4 @@
+{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

tokenizer.json

@@ -58,13 +58,23 @@
       "special": true
     }
   ],
-  "normalizer": null,
-  "pre_tokenizer": {
-    "type": "Metaspace",
-    "replacement": "▁",
-    "prepend_scheme": "first",
-    "split": false
+  "normalizer": {
+    "type": "Sequence",
+    "normalizers": [
+      {
+        "type": "Prepend",
+        "prepend": "▁"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": " "
+        },
+        "content": "▁"
+      }
+    ]
   },
+  "pre_tokenizer": null,
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [

tokenizer_config.json

@@ -57,11 +57,10 @@
     "<|im_end|>"
   ],
   "bos_token": "<|im_start|>",
-  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
-  "legacy": false,
+  "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|im_end|>",
   "sp_model_kwargs": {},