{
  "add_gumbel_noise": true,
  "architectures": [
    "RavenForCausalLM"
  ],
  "attn": null,
  "attnres_block_size": null,
  "bias_rmm": false,
  "bos_token_id": 1,
  "clamp_max": null,
  "clamp_min": null,
  "conv_size": 4,
  "decay_type": "Mamba2",
  "elementwise_affine": false,
  "eos_token_id": 2,
  "expand_k": 1.0,
  "expand_v": 1.0,
  "feature_map": "swish",
  "fuse_cross_entropy": true,
  "fuse_linear_cross_entropy": false,
  "fuse_norm": true,
  "fuse_swiglu": true,
  "gate_logit_normalizer": 4,
  "hidden_act": "swish",
  "hidden_ratio": 4,
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": null,
  "max_position_embeddings": 2048,
  "model_type": "raven",
  "norm_eps": 1e-06,
  "num_heads": 4,
  "num_hidden_layers": 24,
  "num_kv_heads": null,
  "num_slots": 256,
  "rope_theta": 10000.0,
  "router_score": "sigmoid",
  "router_type": "lin",
  "share_conv_kernel": true,
  "tau": 1.0,
  "tie_word_embeddings": false,
  "topk": 64,
  "torch_dtype": "float32",
  "transformers_version": "4.55.4",
  "use_cache": true,
  "use_l2warp": false,
  "use_norm": true,
  "use_output_gate": true,
  "use_rope": false,
  "use_short_conv": false,
  "vocab_size": 32000
}