config.json

{
    "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": true,
    "axial_pos_embds_dim": [
      64,
      960
    ],
    "axial_pos_shape": [
      64,
      64
    ],
    "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": 0.1,
    "hidden_size": 1024,
    "initializer_range": 0.02,
    "is_decoder": true,
    "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": 4096,
    "model_type": "reformer",
    "num_attention_heads": 16,
    "num_buckets": null,
    "num_hashes": 1,
    "num_hidden_layers": 6,
    "pad_token_id": 0,
    "tie_word_embeddings": false,
    "transformers_version": "4.42.4",
    "type_vocab_size": 2,
    "use_cache": true,
    "vocab_size": 30522
  }