tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<repo_name>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<reponame>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": "<file_sep>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": "<filename>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "7": {
      "content": "<potentially_harmful_content>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "8": {
      "content": "<issue_start>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "9": {
      "content": "<issue_comment>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "10": {
      "content": "<issue_closed>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "11": {
      "content": "<jupyter_start>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "12": {
      "content": "<jupyter_text>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13": {
      "content": "<jupyter_code>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "14": {
      "content": "<jupyter_output>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "15": {
      "content": "<jupyter_script>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "16": {
      "content": "<empty_output>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|endoftext|>",
    "<|im_start|>",
    "<|im_end|>",
    "<repo_name>",
    "<reponame>",
    "<file_sep>",
    "<filename>",
    "<potentially_harmful_content>",
    "<issue_start>",
    "<issue_comment>",
    "<issue_closed>",
    "<jupyter_start>",
    "<jupyter_text>",
    "<jupyter_code>",
    "<jupyter_output>",
    "<jupyter_script>",
    "<empty_output>"
  ],
  "bos_token": "<|im_start|>",
  "chat_template": "<|im_start|>system\nYou are a helpful AI assistant named SafeSmolLM, trained by CMU.\n<|im_end|>\n{% for message in messages if message['role'] != 'system' %}\n  {% if message['role'] == 'user' %}\n<|im_start|>user\n{{ message['content'] }}\n<|im_end|>\n  {% elif message['role'] == 'assistant' %}\n<|im_start|>assistant\n{{ message['content'] }}{% if not loop.last or not add_generation_prompt %}<|im_end|>{% endif %}\n  {% endif %}\n  {% if loop.last and add_generation_prompt %}\n<|im_start|>assistant\n  {% endif %}\n{% endfor %}\n",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|im_end|>",
  "extra_special_tokens": {},
  "model_max_length": 8192,
  "pad_token": "<|im_end|>",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>",
  "vocab_size": 49152
}