tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "50256": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50257": {
      "content": "<TITLE_START>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50258": {
      "content": "<TITLE_END>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50259": {
      "content": "<INSTR_START>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50260": {
      "content": "<NEXT_INSTR>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50261": {
      "content": "<INSTR_END>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50262": {
      "content": "<RECIPE_START>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50263": {
      "content": "<RECIPE_END>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50264": {
      "content": "<INPUT_START>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50265": {
      "content": "<INPUT_END>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50266": {
      "content": "<NEXT_INPUT>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50267": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<TITLE_START>",
    "<TITLE_END>",
    "<INSTR_START>",
    "<NEXT_INSTR>",
    "<INSTR_END>",
    "<RECIPE_START>",
    "<RECIPE_END>",
    "<INPUT_START>",
    "<INPUT_END>",
    "<NEXT_INPUT>"
  ],
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|endoftext|>",
  "model_max_length": 1024,
  "pad_token": "<pad>",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}