{
  "_name_or_path": "robingeibel/reformer-finetuned-big_patent-wikipedia-arxiv-16384",
  "architectures": [
    "ReformerForMaskedLM"
  ],
  "attention_head_size": 64,
  "attention_probs_dropout_prob": 0.1,
  "attn_layers": [
    "local",
    "lsh",
    "local",
    "lsh",
    "local",
    "lsh"
  ],
  "axial_norm_std": 1.0,
  "axial_pos_embds": false,
  "axial_pos_embds_dim": [
    128,
    128
  ],
  "axial_pos_shape": [
    512,
    1024
  ],
  "chunk_size_lm_head": 0,
  "classifier_dropout": null,
  "eos_token_id": 2,
  "feed_forward_size": 512,
  "hash_seed": null,
  "hidden_act": "relu",
  "hidden_dropout_prob": 0.05,
  "hidden_size": 256,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-12,
  "local_attention_probs_dropout_prob": 0.05,
  "local_attn_chunk_length": 64,
  "local_num_chunks_after": 0,
  "local_num_chunks_before": 1,
  "lsh_attention_probs_dropout_prob": 0.0,
  "lsh_attn_chunk_length": 64,
  "lsh_num_chunks_after": 0,
  "lsh_num_chunks_before": 1,
  "max_position_embeddings": 16384,
  "model_type": "reformer",
  "num_attention_heads": 2,
  "num_buckets": [
    64,
    128
  ],
  "num_chunks_after": 0,
  "num_chunks_before": 1,
  "num_hashes": 1,
  "num_hidden_layers": 6,
  "output_past": true,
  "pad_token_id": 0,
  "task_specific_params": {
    "text-generation": {
      "do_sample": true,
      "max_length": 100
    }
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.20.1",
  "use_cache": true,
  "vocab_size": 52000
}