tokenizer_config.json

{
  "add_bos_token": false,
  "add_prefix_space": false,
  "afn": "gelu",
  "bos_token": {
    "__type": "AddedToken",
    "content": "<|endoftext|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "__type": "AddedToken",
    "content": "<|endoftext|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "errors": "replace",
  "max_len": 1024,
  "model_max_length": 1024,
  "model_type": "gpt2",
  "n_ctx": 1024,
  "n_embd": 768,
  "n_head": 12,
  "n_layer": 12,
  "n_positions": 1024,
  "name_or_path": "babytoken2",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token": null,
  "special_tokens_map_file": null,
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": {
    "__type": "AddedToken",
    "content": "<|endoftext|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "vocab_size": 32001
}