tokenizer_config.json

{
  "backend": "tokenizers",
  "bos_token": "<|begin_of_text|>",
  "chat_template": "{{ bos_token }}\n{%- for message in messages -%}\n{%- if message['role'] == 'assistant' -%}\n    <|start_header_id|>{{ message['role'] }}<|end_header_id|>\n{% generation %}{{- message['content'] | trim }}<|eot_id|>{% endgeneration %}\n\n{% else %}\n<|start_header_id|>{{ message['role'] }}<|end_header_id|>\n{{ message['content'] | trim }}<|eot_id|>\n{% endif %}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n<|start_header_id|>assistant<|end_header_id|>\n{% endif -%}",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|end_of_text|>",
  "is_local": false,
  "local_files_only": false,
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 131072,
  "tokenizer_class": "PreTrainedTokenizerFast"
}