tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [],
  "bos_token": "<s>",
  "chat_template": "<|system|>\n{{ system_message }}</s>\n<|user|>\n{{ user_message }}</s>\n<|assistant|>\n{{ assistant_message }}</s>\n",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "legacy": true,
  "model_max_length": 32768,
  "pad_token": null,
  "sp_model_kwargs": {},
  "spaces_between_special_tokens": false,
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": "<unk>",
  "use_default_system_prompt": false,
  "custom_tokens": {
    "industrial_terms": [
      "işçilik",
      "malzeme",
      "maliyet",
      "marj",
      "teklif",
      "kaynakçı",
      "teknisyen",
      "mühendis",
      "bakır",
      "kablo",
      "çelik",
      "beton"
    ]
  }
}