{
  "activation_checkpoint_impl": "per-iteration",
  "architecture_class_name": "RecurrentGPT",
  "architectures": [
    "RavenForCausalLM"
  ],
  "attn_impl": "sdpa",
  "attn_logit_softcapping": null,
  "auto_map": {
    "AutoConfig": "raven_config_minimal.RavenConfig",
    "AutoModelForCausalLM": "raven_modeling_minimal.RavenForCausalLM"
  },
  "bias": false,
  "block_class_name": "SandwichBlock",
  "block_size": 4096,
  "block_type": "prenorm",
  "compare_mode": false,
  "effective_expected_depth": 200,
  "final_logit_softcapping": null,
  "head_dim": 64,
  "init_orthogonal": false,
  "init_strategy": "takase",
  "init_values": {
    "embed_scale": 1.0,
    "embedding": 0.013975424859373685,
    "out_proj": 0.0006987712429686843,
    "std": 0.013975424859373685
  },
  "injection_type": "linear",
  "intermediate_size": 8192,
  "max_position_embeddings": 131072,
  "mean_backprop_depth": 8,
  "mean_recurrence": 16,
  "mlp_class_name": "GatedMLP",
  "model_type": "huginn_raven",
  "n_embd": 2048,
  "n_heads": 32,
  "n_layers": 14,
  "n_layers_in_coda": 4,
  "n_layers_in_prelude": 4,
  "n_layers_in_recurrent_block": 6,
  "nonlin_name": "SiLU",
  "norm_class_name": "RMSNorm_llama",
  "norm_eps": 1e-05,
  "norm_type": "llama",
  "num_key_value_heads": 8,
  "padded_vocab_size": 128256,
  "padding_multiple": 4096,
  "qk_bias": false,
  "query_pre_attn_scalar": null,
  "rope_base": 500000.0,
  "rope_scaling": {
    "factor": 32.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "sampling_scheme": "poisson-lognormal-filling",
  "source_arch": "llama",
  "state_init": "like-init",
  "test_time_noise": 0,
  "test_time_noise_type": "fixed",
  "tie_embeddings": false,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.0",
  "vocab_size": 128256
}