tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "additional_special_tokens": [
    "▁▁"
  ],
  "bos_token": {
    "__type": "AddedToken",
    "content": "<|startoftext|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": false,
  "eos_token": {
    "__type": "AddedToken",
    "content": "<|endoftext|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "legacy": null,
  "model_max_length": 8192,
  "pad_token": {
    "__type": "AddedToken",
    "content": "<|pad|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "padding_side": "right",
  "processor_class": "GitProcessor",
  "sp_model_kwargs": {},
  "tokenizer_class": "LlamaTokenizer",
  "truncation": false,
  "unk_token": {
    "__type": "AddedToken",
    "content": "<|unknown|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}