tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "bos_token": {
    "__type": "AddedToken",
    "content": "<｜begin▁of▁sentence｜>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": false,
  "eos_token": {
    "__type": "AddedToken",
    "content": "<｜end▁of▁sentence｜>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "legacy": true,
  "model_max_length": 16384,
  "pad_token": {
    "__type": "AddedToken",
    "content": "<｜end▁of▁sentence｜>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "sp_model_kwargs": {},
  "unk_token": null,
  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
  "tokenizer_class": "LlamaTokenizerFast"
}