Upload tokenizer

special_tokens_map.json

@@ -13,6 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -29,11 +29,12 @@
     }
   },
   "bos_token": "<s>",
+  "chat_template": "{%- for message in messages %}\n{%- if message['role'] == 'user' %}\n{{ bos_token + 'ユーザ：' + message['content'] + eos_token }}\n{%- elif message['role'] == 'assistant' %}\n{{ bos_token + 'アシスタント：'  + message['content'] + eos_token }}\n{%- endif %}\n{% if loop.last and add_generation_prompt %}\n{{ bos_token + 'アシスタント：' }}\n{%- endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
+  "pad_token": "<unk>",
   "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,