{
  "_name_or_path": "configs/hybrid_gated_delta_net_nsa_340M_c4K.json",
  "architectures": [
    "HybridGatedDeltaNetForCausalLM"
  ],
  "attn": {
    "attn_type": "nsa",
    "block_counts": 16,
    "block_size": 64,
    "head_dim": 64,
    "layers": [
      1,
      3,
      5,
      7,
      9,
      11,
      13,
      15,
      17,
      19,
      21,
      23
    ],
    "num_heads": 32,
    "num_kv_heads": 2,
    "qkv_bias": false,
    "rope_theta": 10000.0,
    "window_size": 512
  },
  "attn_mode": "chunk",
  "bos_token_id": 1,
  "conv_size": 4,
  "eos_token_id": 2,
  "expand_v": 1,
  "fuse_cross_entropy": true,
  "fuse_norm": true,
  "fuse_swiglu": true,
  "head_dim": 128,
  "hidden_act": "swish",
  "hidden_ratio": 4,
  "hidden_size": 1024,
  "initializer_range": 0.006,
  "intermediate_size": null,
  "max_position_embeddings": 4096,
  "model_type": "hybrid_gated_deltanet",
  "norm_eps": 1e-06,
  "norm_first": false,
  "num_heads": 8,
  "num_hidden_layers": 24,
  "qk_activation": "silu",
  "qk_norm": "l2",
  "tie_word_embeddings": true,
  "torch_dtype": "float32",
  "transformers_version": "4.49.0",
  "use_beta": true,
  "use_cache": true,
  "use_gate": true,
  "use_output_norm": true,
  "use_short_conv": true,
  "vocab_size": 32000
}