Upload tokenizer

special_tokens_map.json

@@ -1,8 +1,4 @@
 {
-  "additional_special_tokens": [
-    "<start_of_turn>",
-    "<end_of_turn>"
-  ],
   "bos_token": {
     "content": "<bos>",
     "lstrip": false,

tokenizer_config.json

@@ -1995,18 +1995,17 @@
       "special": false
     }
   },
-  "additional_special_tokens": [
-    "<start_of_turn>",
-    "<end_of_turn>"
-  ],
   "bos_token": "<bos>",
-  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
   "extra_special_tokens": {},
+  "max_length": null,
   "model_max_length": 8192,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
-  "padding_side": "right",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",