tokenizer_config.json

{
  "errors": "replace",
  "unk_token": {
    "content": "<|endoftext|>",
    "single_word": false,
    "lstrip": false,
    "rstrip": false,
    "normalized": true,
    "__type": "AddedToken"
  },
  "bos_token": {
    "content": "<|endoftext|>",
    "single_word": false,
    "lstrip": false,
    "rstrip": false,
    "normalized": true,
    "__type": "AddedToken"
  },
  "eos_token": {
    "content": "<|endoftext|>",
    "single_word": false,
    "lstrip": false,
    "rstrip": false,
    "normalized": true,
    "__type": "AddedToken"
  },
  "add_prefix_space": false,
  "pad_token": "<|endoftext|>",
  "cls_token": "<|cls|>",
  "sep_token": "<|sep|>",
  "special_tokens_map_file": null,
  "full_tokenizer_file": null,
  "tokenizer_file": "/home/af1tang/convogym/checkpoint/model/tokenizer.json",
  "name_or_path": "/home/af1tang/convogym/checkpoint/model/",
  "tokenizer_class": "GPT2Tokenizer",
  "chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}"
}