{
  "architectures": [
    "BigBirdForCausalLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "attention_type": "block_sparse",
  "block_size": 64,
  "bos_token_id": 1,
  "classifier_dropout": null,
  "eos_token_id": 2,
  "hidden_act": "gelu_new",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "is_decoder": true,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 4096,
  "model_type": "big_bird",
  "num_attention_heads": 12,
  "num_hidden_layers": 24,
  "num_random_blocks": 3,
  "pad_token_id": 3,
  "rescale_embeddings": false,
  "sep_token_id": 4,
  "torch_dtype": "float32",
  "transformers_version": "4.24.0",
  "type_vocab_size": 2,
  "use_bias": true,
  "use_cache": true,
  "vocab_size": 40000
}