Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|assistant|>": 49153,
+  "<|user|>": 49152
+}

special_tokens_map.json

@@ -1,7 +1,7 @@
 {
   "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
+    "<|user|>",
+    "<|assistant|>"
   ],
   "bos_token": {
     "content": "<|im_start|>",

tokenizer.json

@@ -167,6 +167,24 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 49152,
+      "content": "<|user|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 49153,
+      "content": "<|assistant|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -136,18 +136,34 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "49152": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49153": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
+    "<|user|>",
+    "<|assistant|>"
   ],
   "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 %}",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|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": {},
-  "max_length": 128,
+  "max_length": 8192,
   "model_max_length": 8192,
   "pad_to_multiple_of": null,
   "pad_token": "<|im_end|>",