tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "bos_token": {
    "__type": "AddedToken",
    "content": "<｜begin▁of▁sentence｜>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": false,
  "eos_token": {
    "__type": "AddedToken",
    "content": "<|EOT|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "legacy": true,
  "model_max_length": 16384,
  "pad_token": {
    "__type": "AddedToken",
    "content": "<｜end▁of▁sentence｜>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "sp_model_kwargs": {},
  "unk_token": null,
  "tokenizer_class": "LlamaTokenizerFast",
  "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set ns.found = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are Cogita, an AI programming assistant developed by Mattia Beltrami, a Computer Science for Management student at the University of Bologna (UNIBO), and you only answer questions related to computer science. For non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}"
}