config.json

{
  "architectures": [
    "HybridQwen3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "dtype": "bfloat16",
  "eos_token_id": 151645,
  "gka_config": {
    "bp_lambda": true,
    "chunk_size": 64,
    "conv_size": 4,
    "gla_rescale": true,
    "head_dim": 128,
    "hidden_size": 4096,
    "norm_eps": 1e-06,
    "num_iter": 30,
    "num_k_heads": 8,
    "num_q_heads": 32,
    "num_v_heads": 8,
    "ridge_strength": 0.02,
    "solver_type": "chebyshev",
    "use_alpha_connection": true,
    "use_beta_gate": true,
    "use_forgetting_gate": true,
    "use_forgetting_gate_kk": true,
    "use_gate": true,
    "use_v_conv": true
  },
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "hybrid_override_pattern": "*-GKA-GKA-GKA-GKA-GKA-GKA-*-*-GKA-GKA-GKA-*-*-*-*-*-*-*-*-*-*-*-*-*-*-GKA-GKA-GKA-*-GKA-GKA-GKA-GKA-GKA-GKA",
  "initializer_range": 0.02,
  "intermediate_size": 12288,
  "layer_types": [
    "*",
    "GKA",
    "GKA",
    "GKA",
    "GKA",
    "GKA",
    "GKA",
    "*",
    "*",
    "GKA",
    "GKA",
    "GKA",
    "*",
    "*",
    "*",
    "*",
    "*",
    "*",
    "*",
    "*",
    "*",
    "*",
    "*",
    "*",
    "*",
    "*",
    "GKA",
    "GKA",
    "GKA",
    "*",
    "GKA",
    "GKA",
    "GKA",
    "GKA",
    "GKA",
    "GKA"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 36,
  "model_type": "hybrid_qwen3",
  "num_attention_heads": 32,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "pad_token_id": null,
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "rope_theta": 5000000,
    "rope_type": "default"
  },
  "sliding_window": null,
  "tie_word_embeddings": false,
  "transformers_version": "5.3.0",
  "use_cache": false,
  "use_sliding_window": false,
  "vocab_size": 151936
}