tokenizer_config.json

{
  "added_tokens_decoder": {
    "64790": {
      "content": "[gMASK]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "64792": {
      "content": "sop",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "64795": {
      "content": "<|user|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64796": {
      "content": "<|assistant|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "64797": {
      "content": "<|observation|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|user|>",
    "<|observation|>"
  ],
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_chatglm.ChatGLMTokenizer",
      null
    ]
  },
  "chat_template": "{% for message in messages %}{% if loop.first %}[gMASK]sop<|{{ message['role'] }}|>\n {{ message['content'] }}{% else %}<|{{ message['role'] }}|>\n {{ message['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}",
  "clean_up_tokenization_spaces": false,
  "do_lower_case": false,
  "eos_token": "</s>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<unk>",
  "padding_side": "left",
  "remove_space": false,
  "split_special_tokens": false,
  "tokenizer_class": "ChatGLMTokenizer",
  "unk_token": "<unk>"
}