tokenizer_config.json

{
  "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
    },
    "137713": {
      "content": "<TOKENS_UNUSED_1>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "137714": {
      "content": "<TOKENS_UNUSED_2>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "137715": {
      "content": "<PAD__1>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "137716": {
      "content": "<PAD__2>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "137717": {
      "content": "<PAD__3>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "137718": {
      "content": "<PAD__4>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "137719": {
      "content": "<PAD__5>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "137720": {
      "content": "<PAD__6>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "137721": {
      "content": "<PAD__7>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "137722": {
      "content": "<PAD__8>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "137723": {
      "content": "<PAD__9>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "137724": {
      "content": "<PAD__10>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "137725": {
      "content": "<PAD__11>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "137726": {
      "content": "<PAD__12>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "137727": {
      "content": "<PAD__13>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<TOKENS_UNUSED_1>",
    "<TOKENS_UNUSED_2>",
    "<PAD__1>",
    "<PAD__2>",
    "<PAD__3>",
    "<PAD__4>",
    "<PAD__5>",
    "<PAD__6>",
    "<PAD__7>",
    "<PAD__8>",
    "<PAD__9>",
    "<PAD__10>",
    "<PAD__11>",
    "<PAD__12>",
    "<PAD__13>"
  ],
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_moss2.Moss2Tokenizer",
      null
    ]
  },
  "bos_token": "<s>",
  "chat_template": "{% set system_message = '<s>' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<TOKENS_UNUSED_1>' + content + '<TOKENS_UNUSED_2>' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "</s>",
  "padding_side": "right",
  "split_special_tokens": false,
  "tokenizer_class": "Moss2Tokenizer",
  "unk_token": "<unk>",
  "use_fast": false
}