special_tokens_map.json

{
  "additional_special_tokens": [
    "<unk>",
    "<image>",
    "</image>",
    "<ref>",
    "</ref>",
    "<box>",
    "</box>",
    "<quad>",
    "</quad>",
    "<point>",
    "</point>",
    "<slice>",
    "</slice>",
    "<image_id>",
    "</image_id>",
    "<unit>",
    "</unit>",
    "<|reserved_0|>",
    "<|reserved_1|>",
    "<|reserved_2|>",
    "<|reserved_3|>",
    "<|reserved_4|>",
    "<|reserved_5|>",
    "<|reserved_6|>",
    "<|reserved_7|>",
    "<|reserved_8|>",
    "<|reserved_9|>",
    "<|reserved_10|>",
    "<|reserved_11|>",
    "<|reserved_12|>",
    "<|reserved_13|>",
    "<|reserved_14|>",
    "<|reserved_15|>",
    "<|reserved_16|>",
    "<|reserved_17|>",
    "<|reserved_18|>",
    "<|reserved_19|>",
    "<|reserved_20|>",
    "<|reserved_21|>",
    "<|reserved_22|>",
    "<|reserved_23|>",
    "<|reserved_24|>",
    "<|reserved_25|>",
    "<|reserved_26|>",
    "<|reserved_27|>",
    "<|reserved_28|>",
    "<|reserved_29|>",
    "<|reserved_30|>",
    "<|reserved_31|>",
    "<|reserved_32|>",
    "<|reserved_33|>",
    "<|reserved_34|>",
    "<|reserved_35|>",
    "<|reserved_36|>",
    "<|reserved_37|>",
    "<|reserved_38|>",
    "<|reserved_39|>",
    "<|reserved_40|>",
    "<|reserved_41|>",
    "<|reserved_42|>",
    "<|reserved_43|>",
    "<|reserved_44|>",
    "<|reserved_45|>",
    "<|reserved_46|>",
    "<|reserved_47|>",
    "<|reserved_48|>",
    "<|reserved_49|>",
    "<|reserved_50|>",
    "<|reserved_51|>",
    "<|reserved_52|>",
    "<|reserved_53|>",
    "<|reserved_54|>",
    "<|reserved_55|>",
    "<|reserved_56|>",
    "<|reserved_57|>",
    "<|reserved_58|>",
    "<|reserved_59|>",
    "<|reserved_60|>",
    "<|reserved_61|>",
    "<|reserved_62|>"
  ],
  "bos_token": {
    "content": "<|im_start|>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "content": "<|im_end|>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "pad_token": {
    "content": "<|endoftext|>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "unk_token": {
    "content": "<unk>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  }
}