tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3462": {
      "content": "user",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "5319": {
      "content": "system",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "127900": {
      "content": "<think>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "127901": {
      "content": "</think>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "127902": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "127903": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "127904": {
      "content": "assistant",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "127905": {
      "content": "BiBo",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "127906": {
      "content": "aloobun",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "127907": {
      "content": "LowIQGenAI",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "127908": {
      "content": "IndieTechie",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "127909": {
      "content": "Swamy",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "127910": {
      "content": "AdarshXs",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    }
  },
  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}\n{% for message in loop_messages %}\n{% if message['role'] not in ['user', 'assistant', 'tool_calls'] %}\n{{ raise_exception('Invalid role: ' + message['role'] + '. Must be user, assistant, or tool_calls.') }}\n{% endif %}\n{% if loop.index0 == 0 and system_message != false %}\n{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}\n{% else %}\n{% set content = message['content'] %}\n{% endif %}\n{% if message['role'] == 'user' %}\n{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}\n{% elif message['role'] == 'assistant' %}\n{{ ' ' + content.strip() + ' ' + eos_token }}\n{% elif message['role'] == 'tool_calls' %}\n{{ ' [TOOL_CALLS] ' + content.strip() + ' [/TOOL_CALLS] ' }}\n{% endif %}\n{% endfor %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "extra_special_tokens": {},
  "model_max_length": 8192,
  "pad_token": "<|endoftext|>",
  "padding_side": "right",
  "tokenizer_class": "PreTrainedTokenizerFast"
}