config.json

{
    "architectures": [
        "Glm4MoeForCausalLM"
    ],
    "attention_bias": true,
    "attention_dropout": 0.0,
    "torch_dtype": "bfloat16",
    "eos_token_id": [
        151329,
        151336,
        151338
    ],
    "first_k_dense_replace": 3,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 5120,
    "initializer_range": 0.02,
    "intermediate_size": 12288,
    "max_position_embeddings": 202752,
    "model_type": "glm4_moe",
    "moe_intermediate_size": 1536,
    "n_group": 1,
    "n_routed_experts": 160,
    "n_shared_experts": 1,
    "norm_topk_prob": true,
    "num_attention_heads": 96,
    "num_experts_per_tok": 8,
    "num_hidden_layers": 92,
    "num_key_value_heads": 8,
    "num_nextn_predict_layers": 1,
    "pad_token_id": 151329,
    "partial_rotary_factor": 0.5,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 1000000,
    "routed_scaling_factor": 2.5,
    "tie_word_embeddings": false,
    "topk_group": 1,
    "transformers_version": "4.57.0",
    "use_cache": true,
    "use_qk_norm": true,
    "vocab_size": 151552,
    "quantization_config": {
        "config_groups": {
            "group_0": {
                "input_activations": {
                    "dynamic": false,
                    "num_bits": 4,
                    "type": "float",
                    "group_size": 16
                },
                "weights": {
                    "dynamic": false,
                    "num_bits": 4,
                    "type": "float",
                    "group_size": 16
                },
                "targets": [
                    "Linear"
                ]
            }
        },
        "ignore": [
            "model.layers.0.self_attn*",
            "model.layers.1.self_attn*",
            "model.layers.10.self_attn*",
            "model.layers.11.self_attn*",
            "model.layers.12.self_attn*",
            "model.layers.13.self_attn*",
            "model.layers.14.self_attn*",
            "model.layers.15.self_attn*",
            "model.layers.16.self_attn*",
            "model.layers.17.self_attn*",
            "model.layers.18.self_attn*",
            "model.layers.19.self_attn*",
            "model.layers.2.self_attn*",
            "model.layers.20.self_attn*",
            "model.layers.21.self_attn*",
            "model.layers.22.self_attn*",
            "model.layers.23.self_attn*",
            "model.layers.24.self_attn*",
            "model.layers.25.self_attn*",
            "model.layers.26.self_attn*",
            "model.layers.27.self_attn*",
            "model.layers.28.self_attn*",
            "model.layers.29.self_attn*",
            "model.layers.3.self_attn*",
            "model.layers.30.self_attn*",
            "model.layers.31.self_attn*",
            "model.layers.32.self_attn*",
            "model.layers.33.self_attn*",
            "model.layers.34.self_attn*",
            "model.layers.35.self_attn*",
            "model.layers.36.self_attn*",
            "model.layers.37.self_attn*",
            "model.layers.38.self_attn*",
            "model.layers.39.self_attn*",
            "model.layers.4.self_attn*",
            "model.layers.40.self_attn*",
            "model.layers.41.self_attn*",
            "model.layers.42.self_attn*",
            "model.layers.43.self_attn*",
            "model.layers.44.self_attn*",
            "model.layers.45.self_attn*",
            "model.layers.46.self_attn*",
            "model.layers.47.self_attn*",
            "model.layers.48.self_attn*",
            "model.layers.49.self_attn*",
            "model.layers.5.self_attn*",
            "model.layers.50.self_attn*",
            "model.layers.51.self_attn*",
            "model.layers.52.self_attn*",
            "model.layers.53.self_attn*",
            "model.layers.54.self_attn*",
            "model.layers.55.self_attn*",
            "model.layers.56.self_attn*",
            "model.layers.57.self_attn*",
            "model.layers.58.self_attn*",
            "model.layers.59.self_attn*",
            "model.layers.6.self_attn*",
            "model.layers.60.self_attn*",
            "model.layers.61.self_attn*",
            "model.layers.62.self_attn*",
            "model.layers.63.self_attn*",
            "model.layers.64.self_attn*",
            "model.layers.65.self_attn*",
            "model.layers.66.self_attn*",
            "model.layers.67.self_attn*",
            "model.layers.68.self_attn*",
            "model.layers.69.self_attn*",
            "model.layers.7.self_attn*",
            "model.layers.70.self_attn*",
            "model.layers.71.self_attn*",
            "model.layers.72.self_attn*",
            "model.layers.73.self_attn*",
            "model.layers.74.self_attn*",
            "model.layers.75.self_attn*",
            "model.layers.76.self_attn*",
            "model.layers.77.self_attn*",
            "model.layers.78.self_attn*",
            "model.layers.79.self_attn*",
            "model.layers.8.self_attn*",
            "model.layers.80.self_attn*",
            "model.layers.81.self_attn*",
            "model.layers.82.self_attn*",
            "model.layers.83.self_attn*",
            "model.layers.84.self_attn*",
            "model.layers.85.self_attn*",
            "model.layers.86.self_attn*",
            "model.layers.87.self_attn*",
            "model.layers.88.self_attn*",
            "model.layers.89.self_attn*",
            "model.layers.9.self_attn*",
            "model.layers.90.self_attn*",
            "model.layers.91.self_attn*",
            "lm_head",
            "model.layers.92*"
        ],
        "quant_algo": "NVFP4",
        "producer": {
            "name": "modelopt",
            "version": "0.37.0.dev82+g340eb7a75"
        },
        "quant_method": "modelopt"
    }
}