tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32000": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32001": {
      "content": "[INST]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32002": {
      "content": "[/INST]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32003": {
      "content": "[EMOTION]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32004": {
      "content": "[/EMOTION]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "[INST]",
    "[/INST]",
    "[EMOTION]",
    "[/EMOTION]"
  ],
  "bos_token": "<s>",
  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content']['dialog'] %}{% set loop_messages = messages[1:] %}{% else %}{% set system_message = '' %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set emotion = message['content']['emotion'] %}{% set dialog = message['content']['dialog'].strip() %}{% if message['role'] == 'user' %}{% if loop.index0 == 0 and system_message != '' %}{{ bos_token + '[INST]<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + '[EMOTION] ' + emotion + ' [/EMOTION] ' + dialog }}{% else %}{{ bos_token + '[INST] [EMOTION] ' + emotion + ' [/EMOTION] ' + dialog }}{% endif %}{% else %}{% if loop.last and add_generation_prompt %}{{ ' [/INST] [EMOTION] ' + emotion + ' [/EMOTION] ' }}{% else %}{{ ' [/INST] [EMOTION] ' + emotion + ' [/EMOTION] ' + dialog + ' ' + eos_token + '\\n' }}{% endif %}{% endif %}{% endfor %}",
  "clean_up_tokenization_spaces": true,
  "eos_token": "</s>",
  "legacy": false,
  "model_max_length": 4096,
  "pad_token": "<pad>",
  "padding_side": "right",
  "sp_model_kwargs": {},
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": "<unk>",
  "use_default_system_prompt": false
}