config.json

{
    "architectures": [
        "Qwen3MoeForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "decoder_sparse_step": 1,
    "eos_token_id": 151645,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 6144,
    "max_position_embeddings": 40960,
    "max_window_layers": 48,
    "mlp_only_layers": [],
    "model_type": "qwen3_moe",
    "moe_intermediate_size": 768,
    "norm_topk_prob": true,
    "num_attention_heads": 32,
    "num_experts": 128,
    "num_experts_per_tok": 8,
    "num_hidden_layers": 48,
    "num_key_value_heads": 4,
    "output_router_logits": false,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000.0,
    "router_aux_loss_coef": 0.001,
    "sliding_window": null,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.51.0",
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 151936,
    "quantization_config": {
        "quant_method": "exl2",
        "version": "0.3.1",
        "bits": 6.0,
        "head_bits": 8,
        "calibration": {
            "rows": 115,
            "length": 2048,
            "dataset": "(default)"
        }
    }
}