{
  "architectures": [
    "ReformerModelWithLMHead"
  ],
  "attention_head_size": 64,
  "attention_probs_dropout_prob": 0.1,
  "attn_type": "mixed",
  "axial_norm_std": 1.0,
  "axial_pos_embds": true,
  "axial_pos_embds_dim": [
    64,
    192
  ],
  "axial_pos_shape": [
    512,
    1024
  ],
  "chunk_length": 64,
  "chunk_size_feed_forward": 64,
  "chunk_size_lm_head": 64,
  "feed_forward_size": 512,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.05,
  "hidden_size": 256,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "is_decoder": true,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 524288,
  "model_type": "bert",
  "num_attention_heads": 2,
  "num_buckets": null,
  "num_chunks_after": 0,
  "num_chunks_before": 1,
  "num_hashes": 4,
  "num_hidden_layers": 6,
  "output_past": true,
  "seed": 0,
  "sinusoidal_pos_embds": false,
  "type_vocab_size": 2,
  "vocab_size": 320
}