Upload tokenizer

special_tokens_map.json

@@ -1,37 +1,28 @@
 {
   "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,
     "single_word": false
   },
-  "pad_token": "<|PAD_TOKEN|>",
-  "unk_token": "�"
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -155,15 +155,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 49152,
-      "content": "<|PAD_TOKEN|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -136,42 +136,20 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "49152": {
-      "content": "<|PAD_TOKEN|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "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|>",
-  "model_max_length": 8192,
-  "pad_token": "<|PAD_TOKEN|>",
+  "eos_token": "<|im_end|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
   "padding_side": "left",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "�",
+  "unk_token": "<|endoftext|>",
   "vocab_size": 49152
 }