tokenizer_config.json

{
  "add_bos_token": false,
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "16": {
      "content": "0",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "17": {
      "content": "1",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "19": {
      "content": "3",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "20": {
      "content": "4",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "36": {
      "content": "D",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "38": {
      "content": "F",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "41": {
      "content": "I",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "43": {
      "content": "K",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "44": {
      "content": "L",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "45": {
      "content": "M",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "46": {
      "content": "N",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "50": {
      "content": "R",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "52": {
      "content": "T",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "59": {
      "content": "_",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "87": {
      "content": "{",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "89": {
      "content": "}",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "50000": {
      "content": "U",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "50001": {
      "content": "Y",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "50002": {
      "content": "X",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": false
    }
  },
  "additional_special_tokens": [],
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|endoftext|>",
  "errors": "replace",
  "keep_accents": true,
  "max_len": 50,
  "model_max_length": 50,
  "pad_token": "<|endoftext|>",
  "tokenizer_class": "GPT2Tokenizer",
  "tokenizer_file": "/home/jl/.cache/huggingface/hub/models--ClassCat--gpt2-base-french/snapshots/902ec822995ce12f979d0a5277ee9c2a1b610df1/tokenizer.json",
  "unk_token": "<|endoftext|>"
}