config.json

{
  "architectures": [
    "HYV3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": null,
  "dtype": "bfloat16",
  "enable_moe_fp32_combine": true,
  "eos_token_id": null,
  "first_k_dense_replace": 1,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 1024,
  "initializer_range": 0.006,
  "intermediate_size": 2816,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "mlp_layer_types": [
    "dense",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse"
  ],
  "model_type": "hy_v3",
  "moe_intermediate_size": 512,
  "moe_router_enable_expert_bias": true,
  "moe_router_use_sigmoid": true,
  "num_attention_heads": 16,
  "num_experts": 64,
  "num_experts_per_tok": 2,
  "num_hidden_layers": 24,
  "num_key_value_heads": 4,
  "num_shared_experts": 4,
  "output_router_logits": false,
  "pad_token_id": null,
  "qk_norm": true,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 1000000.0,
    "rope_type": "default"
  },
  "route_norm": true,
  "router_scaling_factor": 2.826,
  "tie_word_embeddings": true,
  "transformers_version": "5.14.1",
  "use_cache": true,
  "vocab_size": 49152
}