Upload tokenizer

README.md

@@ -1,10 +1,10 @@
 ---
 license: apache-2.0
-base_model: yanolja/EEVE-Korean-Instruct-10.8B-v1.0
 tags:
 - trl
 - dpo
 - generated_from_trainer
+base_model: yanolja/EEVE-Korean-Instruct-10.8B-v1.0
 model-index:
 - name: nhn_dpo_v3-eeve_EEVE-Korean-Instruct-10.8B-v1.0_DPO
   results: []

special_tokens_map.json

@@ -7,7 +7,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -37,13 +37,12 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = \"A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.\" %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{system_message + '\n'}}{% endif %}{% if message['role'] == 'user' %}{{'Human: ' + message['content']+'\n'}}{% elif message['role'] == 'assistant' %}{{'Assistant: '  + message['content']+'\n'}}{% endif %}{% if loop.last and add_generation_prompt %}{{'Assistant: ' }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "</s>",
   "legacy": true,
-  "model_max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
-  "padding_size": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",