tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64256": {
      "content": "<|alku|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "64257": {
      "content": "<PAD>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64258": {
      "content": "<|ihminen|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "64259": {
      "content": "<|avustaja|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "64260": {
      "content": "<|loppu|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64261": {
      "content": "\n",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|loppu|>",
  "max_length": 25000,
  "model_max_length": 2048,
  "pad_to_multiple_of": null,
  "pad_token": "<|loppu|>",
  "pad_token_type_id": 0,
  "padding_side": "right",
  "sp_model_kwargs": {},
  "stride": 0,
  "tokenizer_class": "LlamaTokenizer",
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "unk_token": "<unk>",
  "use_default_system_prompt": false
}