tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "add_prefix_space": true,
  "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
    },
    "61366": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "61367": {
      "content": "<|system|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "61368": {
      "content": "<|user|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "61369": {
      "content": "<|assistant|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "61370": {
      "content": "<|context|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "61371": {
      "content": "<|/context|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "61372": {
      "content": "[INST]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "61373": {
      "content": "[/INST]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "61374": {
      "content": "<|translate-en-el|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "61375": {
      "content": "<|translate-el-en|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "61376": {
      "content": "<|tldr|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|system|>",
    "<|user|>",
    "<|assistant|>",
    "<|context|>",
    "<|/context|>",
    "[INST]",
    "[/INST]",
    "<|translate-en-el|>",
    "<|translate-el-en|>",
    "<|tldr|>"
  ],
  "bos_token": "<s>",
  "chat_template": "{% if 'role' in messages[0] %}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + eos_token + '\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>\n' + message['content'] + eos_token + '\n' }}{% else %}{{ '<|system|>\n' + message['content'] + eos_token + '\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% else %}{% for message in messages %}{% if message['from'] == 'human' %}{{ '<|user|>\n' + message['value'] + eos_token + '\n' }}{% elif message['from'] == 'gpt' %}{{ '<|assistant|>\n' + message['value'] + eos_token + '\n' }}{% else %}{{ '<|system|>\n' + message['value'] + eos_token + '\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endif %}",
  "clean_up_tokenization_spaces": false,
  "cls_token": "<s>",
  "eos_token": "</s>",
  "legacy": false,
  "mask_token": "<unk>",
  "model_max_length": 32768,
  "pad_token": "<pad>",
  "padding_side": "left",
  "sep_token": "</s>",
  "sp_model_kwargs": {},
  "spaces_between_special_tokens": false,
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": "<unk>",
  "use_default_system_prompt": false,
  "use_fast": true
}