Upload tokenizer

special_tokens_map.json

@@ -1,32 +1,17 @@
 {
   "additional_special_tokens": [
-    "<|endoftext|>",
     "<|im_start|>",
-    "<|im_end|>",
-    "<repo_name>",
-    "<reponame>",
-    "<file_sep>",
-    "<filename>",
-    "<gh_stars>",
-    "<issue_start>",
-    "<issue_comment>",
-    "<issue_closed>",
-    "<jupyter_start>",
-    "<jupyter_text>",
-    "<jupyter_code>",
-    "<jupyter_output>",
-    "<jupyter_script>",
-    "<empty_output>"
+    "<|im_end|>"
   ],
   "bos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|im_start|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -155,27 +155,13 @@
     }
   },
   "additional_special_tokens": [
-    "<|endoftext|>",
     "<|im_start|>",
-    "<|im_end|>",
-    "<repo_name>",
-    "<reponame>",
-    "<file_sep>",
-    "<filename>",
-    "<gh_stars>",
-    "<issue_start>",
-    "<issue_comment>",
-    "<issue_closed>",
-    "<jupyter_start>",
-    "<jupyter_text>",
-    "<jupyter_code>",
-    "<jupyter_output>",
-    "<jupyter_script>",
-    "<empty_output>"
+    "<|im_end|>"
   ],
-  "bos_token": "<|endoftext|>",
+  "bos_token": "<|im_start|>",
+  "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": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "model_max_length": 16384,
   "pad_token": "<|PAD_TOKEN|>",
   "padding_side": "left",