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
    },
    "92544": {
      "content": "<|user|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "92545": {
      "content": "<|system|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "92546": {
      "content": "<|assistant|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "92547": {
      "content": "<|text|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "92548": {
      "content": "<|code|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "92549": {
      "content": "<|execution|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "92550": {
      "content": "<|endofblock|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "92551": {
      "content": "<|endofmessage|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|user|>",
    "<|system|>",
    "<|assistant|>",
    "<|text|>",
    "<|code|>",
    "<|execution|>",
    "<|endofblock|>",
    "<|endofmessage|>"
  ],
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_internlm2.InternLM2Tokenizer",
      "tokenization_internlm2_fast.InternLM2TokenizerFast"
    ]
  },
  "bos_token": "<s>",
  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>' }}{% elif message['role'] == 'system' %}\n{{ '<|system|>' }}{% elif message['role'] == 'assistant_correct' %}\n{{ '<|assistant|>' }}{% endif %}\n{% for block in message['content'] %}\n{% if block['type'] == 'text' %}\n{{ '<|text|>' }}{% elif block['type'] == 'code' %}\n{{ '<|code|>' }}{% elif block['type'] == 'execution' %}\n{{ '<|execution|>' }}{% endif %}\n{{ block['content'] + '<|endofblock|>' }}{% endfor %}\n{% if message['role'] != 'assistant_correct' %}\n{{ '<|endofmessage|>' }}{% endif %}{% endfor %}",
  "clean_up_tokenization_spaces": false,
  "decode_with_prefix_space": false,
  "eos_token": "</s>",
  "model_max_length": 2048,
  "pad_token": "</s>",
  "sp_model_kwargs": null,
  "tokenizer_class": "InternLM2Tokenizer",
  "unk_token": "<unk>"
}