Update tokenizer_config.json

tokenizer_config.json

@@ -779,13 +779,10 @@
     }
   },
   "bos_token": "<|endoftext|>",
-  "chat_template": "{% if 'role' in messages[0] %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<｜User｜>' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{{ '<｜Assistant｜>' + message['content'] + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<｜Assistant｜>' }}{% endif %}{% else %}{{ bos_token }}{% for message in messages %}{% if message['from'] == 'system' %}{{ message['value'] + '\n' }}{% elif message['from'] == 'user' %}{{ '<｜User｜>' + message['value'] + '\n' }}{% elif message['from'] == 'gpt' %}{{ '<｜Assistant｜>' + message['value'] + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<｜Assistant｜>' }}{% endif %}{% endif %}",
+  "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
-  "extra_special_tokens": {},
-  "model_max_length": 35000,
-  "pad_token": "<|dummy_87|>",
-  "padding_side": "left",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "�"
+  "model_max_length": 16384,
+  "pad_token": "<|dummy_85|>",
+  "tokenizer_class": "GPT2Tokenizer"
 }