tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "add_prefix_space": null,
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<s>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32000": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32001": {
      "content": "<|im_start|>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [],
  "bos_token": "<s>",
  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|im_end|>",
  "legacy": true,
  "max_length": 4096,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<unk>",
  "sp_model_kwargs": {},
  "spaces_between_special_tokens": false,
  "stride": 0,
  "tokenizer_class": "LlamaTokenizer",
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "trust_remote_code": false,
  "unk_token": "<unk>",
  "use_default_system_prompt": false,
  "use_fast": true
}