vocab/dbrx_instruct/dbrx-instruct/tokenizer_config.json

{
  "add_bos_token": false,
  "add_eos_token": false,
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "100257": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100277": {
      "content": "<|pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100278": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100279": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|im_start|>",
    "<|im_end|>"
  ],
  "auto_map": {
    "AutoTokenizer": [
      "tiktoken.TiktokenTokenizerWrapper",
      null
    ]
  },
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": true,
  "encoding_name": null,
  "eos_token": "<|endoftext|>",
  "errors": "replace",
  "model_max_length": 1000000000000000019884624838656,
  "model_name": "gpt-4",
  "pad_token": "<|pad|>",
  "tokenizer_class": "TiktokenTokenizerWrapper",
  "unk_token": "<|endoftext|>",
  "use_default_system_prompt": true
}