{ "architectures": [ "Glm4MoeForCausalLM" ], "attention_bias": true, "attention_dropout": 0.0, "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, "no_split_module_classes": [ "MergedColumnParallelLinear" ], "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": 0, "pad_token_id": 151329, "partial_rotary_factor": 0.5, "quantization_config": { "config_groups": { "group_0": { "format": "pack-quantized", "input_activations": null, "output_activations": null, "targets": [ "Linear", "re:.*gate_proj.*", "re:.*up_proj.*", "re:.*down_proj.*", "re:.*k_proj.*", "re:.*q_proj.*", "re:.*v_proj.*", "re:.*o_proj.*" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": 128, "num_bits": 4, "observer": "minmax", "observer_kwargs": {}, "strategy": "group", "symmetric": true, "type": "int" } } }, "format": "pack-quantized", "global_compression_ratio": null, "ignore": [ "model.layers.0.self_attn.q_proj", "model.layers.0.self_attn.k_proj", "model.layers.0.self_attn.v_proj", "model.layers.0.self_attn.o_proj", "model.layers.0.mlp.gate_proj", "model.layers.0.mlp.up_proj", "model.layers.0.mlp.down_proj", "model.layers.1.self_attn.q_proj", "model.layers.1.self_attn.k_proj", "model.layers.1.self_attn.v_proj", "model.layers.1.self_attn.o_proj", "model.layers.1.mlp.gate_proj", "model.layers.1.mlp.up_proj", "model.layers.1.mlp.down_proj", "model.layers.2.self_attn.q_proj", "model.layers.2.self_attn.k_proj", "model.layers.2.self_attn.v_proj", "model.layers.2.self_attn.o_proj", "model.layers.2.mlp.gate_proj", "model.layers.2.mlp.up_proj", "model.layers.2.mlp.down_proj", "model.layers.3.mlp.shared_experts.gate_proj", "model.layers.3.mlp.shared_experts.up_proj", "model.layers.3.mlp.shared_experts.down_proj", "model.layers.4.mlp.shared_experts.gate_proj", "model.layers.4.mlp.shared_experts.up_proj", "model.layers.4.mlp.shared_experts.down_proj", "model.layers.5.mlp.shared_experts.gate_proj", "model.layers.5.mlp.shared_experts.up_proj", "model.layers.5.mlp.shared_experts.down_proj", "model.layers.6.mlp.shared_experts.gate_proj", "model.layers.6.mlp.shared_experts.up_proj", "model.layers.6.mlp.shared_experts.down_proj", "model.layers.7.mlp.shared_experts.gate_proj", "model.layers.7.mlp.shared_experts.up_proj", "model.layers.7.mlp.shared_experts.down_proj", "model.layers.8.mlp.shared_experts.gate_proj", "model.layers.8.mlp.shared_experts.up_proj", "model.layers.8.mlp.shared_experts.down_proj", "model.layers.9.mlp.shared_experts.gate_proj", "model.layers.9.mlp.shared_experts.up_proj", "model.layers.9.mlp.shared_experts.down_proj", "model.layers.10.mlp.shared_experts.gate_proj", "model.layers.10.mlp.shared_experts.up_proj", "model.layers.10.mlp.shared_experts.down_proj", "model.layers.11.mlp.shared_experts.gate_proj", "model.layers.11.mlp.shared_experts.up_proj", "model.layers.11.mlp.shared_experts.down_proj", "model.layers.12.mlp.shared_experts.gate_proj", "model.layers.12.mlp.shared_experts.up_proj", "model.layers.12.mlp.shared_experts.down_proj", "model.layers.13.mlp.shared_experts.gate_proj", "model.layers.13.mlp.shared_experts.up_proj", "model.layers.13.mlp.shared_experts.down_proj", "model.layers.14.mlp.shared_experts.gate_proj", "model.layers.14.mlp.shared_experts.up_proj", "model.layers.14.mlp.shared_experts.down_proj", "model.layers.15.mlp.shared_experts.gate_proj", "model.layers.15.mlp.shared_experts.up_proj", "model.layers.15.mlp.shared_experts.down_proj", "model.layers.16.mlp.shared_experts.gate_proj", "model.layers.16.mlp.shared_experts.up_proj", "model.layers.16.mlp.shared_experts.down_proj", "model.layers.17.mlp.shared_experts.gate_proj", "model.layers.17.mlp.shared_experts.up_proj", "model.layers.17.mlp.shared_experts.down_proj", "model.layers.18.mlp.shared_experts.gate_proj", "model.layers.18.mlp.shared_experts.up_proj", "model.layers.18.mlp.shared_experts.down_proj", "model.layers.19.mlp.shared_experts.gate_proj", "model.layers.19.mlp.shared_experts.up_proj", "model.layers.19.mlp.shared_experts.down_proj", "model.layers.20.mlp.shared_experts.gate_proj", "model.layers.20.mlp.shared_experts.up_proj", "model.layers.20.mlp.shared_experts.down_proj", "model.layers.21.mlp.shared_experts.gate_proj", "model.layers.21.mlp.shared_experts.up_proj", "model.layers.21.mlp.shared_experts.down_proj", "model.layers.22.mlp.shared_experts.gate_proj", "model.layers.22.mlp.shared_experts.up_proj", "model.layers.22.mlp.shared_experts.down_proj", "model.layers.23.mlp.shared_experts.gate_proj", "model.layers.23.mlp.shared_experts.up_proj", "model.layers.23.mlp.shared_experts.down_proj", "model.layers.24.mlp.shared_experts.gate_proj", "model.layers.24.mlp.shared_experts.up_proj", "model.layers.24.mlp.shared_experts.down_proj", "model.layers.25.mlp.shared_experts.gate_proj", "model.layers.25.mlp.shared_experts.up_proj", "model.layers.25.mlp.shared_experts.down_proj", "model.layers.26.mlp.shared_experts.gate_proj", "model.layers.26.mlp.shared_experts.up_proj", "model.layers.26.mlp.shared_experts.down_proj", "model.layers.27.mlp.shared_experts.gate_proj", "model.layers.27.mlp.shared_experts.up_proj", "model.layers.27.mlp.shared_experts.down_proj", "model.layers.28.mlp.shared_experts.gate_proj", "model.layers.28.mlp.shared_experts.up_proj", "model.layers.28.mlp.shared_experts.down_proj", "model.layers.29.mlp.shared_experts.gate_proj", "model.layers.29.mlp.shared_experts.up_proj", "model.layers.29.mlp.shared_experts.down_proj", "model.layers.30.mlp.shared_experts.gate_proj", "model.layers.30.mlp.shared_experts.up_proj", "model.layers.30.mlp.shared_experts.down_proj", "model.layers.31.mlp.shared_experts.gate_proj", "model.layers.31.mlp.shared_experts.up_proj", "model.layers.31.mlp.shared_experts.down_proj", "model.layers.32.mlp.shared_experts.gate_proj", "model.layers.32.mlp.shared_experts.up_proj", "model.layers.32.mlp.shared_experts.down_proj", "model.layers.33.mlp.shared_experts.gate_proj", "model.layers.33.mlp.shared_experts.up_proj", "model.layers.33.mlp.shared_experts.down_proj", "model.layers.34.mlp.shared_experts.gate_proj", "model.layers.34.mlp.shared_experts.up_proj", "model.layers.34.mlp.shared_experts.down_proj", "model.layers.35.mlp.shared_experts.gate_proj", "model.layers.35.mlp.shared_experts.up_proj", "model.layers.35.mlp.shared_experts.down_proj", "model.layers.36.mlp.shared_experts.gate_proj", "model.layers.36.mlp.shared_experts.up_proj", "model.layers.36.mlp.shared_experts.down_proj", "model.layers.37.mlp.shared_experts.gate_proj", "model.layers.37.mlp.shared_experts.up_proj", "model.layers.37.mlp.shared_experts.down_proj", "model.layers.38.mlp.shared_experts.gate_proj", "model.layers.38.mlp.shared_experts.up_proj", "model.layers.38.mlp.shared_experts.down_proj", "model.layers.39.mlp.shared_experts.gate_proj", "model.layers.39.mlp.shared_experts.up_proj", "model.layers.39.mlp.shared_experts.down_proj", "model.layers.40.mlp.shared_experts.gate_proj", "model.layers.40.mlp.shared_experts.up_proj", "model.layers.40.mlp.shared_experts.down_proj", "model.layers.41.mlp.shared_experts.gate_proj", "model.layers.41.mlp.shared_experts.up_proj", "model.layers.41.mlp.shared_experts.down_proj", "model.layers.42.mlp.shared_experts.gate_proj", "model.layers.42.mlp.shared_experts.up_proj", "model.layers.42.mlp.shared_experts.down_proj", "model.layers.43.mlp.shared_experts.gate_proj", "model.layers.43.mlp.shared_experts.up_proj", "model.layers.43.mlp.shared_experts.down_proj", "model.layers.44.mlp.shared_experts.gate_proj", "model.layers.44.mlp.shared_experts.up_proj", "model.layers.44.mlp.shared_experts.down_proj", "model.layers.45.mlp.shared_experts.gate_proj", "model.layers.45.mlp.shared_experts.up_proj", "model.layers.45.mlp.shared_experts.down_proj", "model.layers.46.mlp.shared_experts.gate_proj", "model.layers.46.mlp.shared_experts.up_proj", "model.layers.46.mlp.shared_experts.down_proj", "model.layers.47.mlp.shared_experts.gate_proj", "model.layers.47.mlp.shared_experts.up_proj", "model.layers.47.mlp.shared_experts.down_proj", "model.layers.48.mlp.shared_experts.gate_proj", "model.layers.48.mlp.shared_experts.up_proj", "model.layers.48.mlp.shared_experts.down_proj", "model.layers.49.mlp.shared_experts.gate_proj", "model.layers.49.mlp.shared_experts.up_proj", "model.layers.49.mlp.shared_experts.down_proj", "model.layers.50.mlp.shared_experts.gate_proj", "model.layers.50.mlp.shared_experts.up_proj", "model.layers.50.mlp.shared_experts.down_proj", "model.layers.51.mlp.shared_experts.gate_proj", "model.layers.51.mlp.shared_experts.up_proj", "model.layers.51.mlp.shared_experts.down_proj", "model.layers.52.mlp.shared_experts.gate_proj", "model.layers.52.mlp.shared_experts.up_proj", "model.layers.52.mlp.shared_experts.down_proj", "model.layers.53.mlp.shared_experts.gate_proj", "model.layers.53.mlp.shared_experts.up_proj", "model.layers.53.mlp.shared_experts.down_proj", "model.layers.54.mlp.shared_experts.gate_proj", "model.layers.54.mlp.shared_experts.up_proj", "model.layers.54.mlp.shared_experts.down_proj", "model.layers.55.mlp.shared_experts.gate_proj", "model.layers.55.mlp.shared_experts.up_proj", "model.layers.55.mlp.shared_experts.down_proj", "model.layers.56.mlp.shared_experts.gate_proj", "model.layers.56.mlp.shared_experts.up_proj", "model.layers.56.mlp.shared_experts.down_proj", "model.layers.57.mlp.shared_experts.gate_proj", "model.layers.57.mlp.shared_experts.up_proj", "model.layers.57.mlp.shared_experts.down_proj", "model.layers.58.mlp.shared_experts.gate_proj", "model.layers.58.mlp.shared_experts.up_proj", "model.layers.58.mlp.shared_experts.down_proj", "model.layers.59.mlp.shared_experts.gate_proj", "model.layers.59.mlp.shared_experts.up_proj", "model.layers.59.mlp.shared_experts.down_proj", "model.layers.60.mlp.shared_experts.gate_proj", "model.layers.60.mlp.shared_experts.up_proj", "model.layers.60.mlp.shared_experts.down_proj", "model.layers.61.mlp.shared_experts.gate_proj", "model.layers.61.mlp.shared_experts.up_proj", "model.layers.61.mlp.shared_experts.down_proj", "model.layers.62.mlp.shared_experts.gate_proj", "model.layers.62.mlp.shared_experts.up_proj", "model.layers.62.mlp.shared_experts.down_proj", "model.layers.63.mlp.shared_experts.gate_proj", "model.layers.63.mlp.shared_experts.up_proj", "model.layers.63.mlp.shared_experts.down_proj", "model.layers.64.mlp.shared_experts.gate_proj", "model.layers.64.mlp.shared_experts.up_proj", "model.layers.64.mlp.shared_experts.down_proj", "model.layers.65.mlp.shared_experts.gate_proj", "model.layers.65.mlp.shared_experts.up_proj", "model.layers.65.mlp.shared_experts.down_proj", "model.layers.66.mlp.shared_experts.gate_proj", "model.layers.66.mlp.shared_experts.up_proj", "model.layers.66.mlp.shared_experts.down_proj", "model.layers.67.mlp.shared_experts.gate_proj", "model.layers.67.mlp.shared_experts.up_proj", "model.layers.67.mlp.shared_experts.down_proj", "model.layers.68.mlp.shared_experts.gate_proj", "model.layers.68.mlp.shared_experts.up_proj", "model.layers.68.mlp.shared_experts.down_proj", "model.layers.69.mlp.shared_experts.gate_proj", "model.layers.69.mlp.shared_experts.up_proj", "model.layers.69.mlp.shared_experts.down_proj", "model.layers.70.mlp.shared_experts.gate_proj", "model.layers.70.mlp.shared_experts.up_proj", "model.layers.70.mlp.shared_experts.down_proj", "model.layers.71.mlp.shared_experts.gate_proj", "model.layers.71.mlp.shared_experts.up_proj", "model.layers.71.mlp.shared_experts.down_proj", "model.layers.72.mlp.shared_experts.gate_proj", "model.layers.72.mlp.shared_experts.up_proj", "model.layers.72.mlp.shared_experts.down_proj", "model.layers.73.mlp.shared_experts.gate_proj", "model.layers.73.mlp.shared_experts.up_proj", "model.layers.73.mlp.shared_experts.down_proj", "model.layers.74.mlp.shared_experts.gate_proj", "model.layers.74.mlp.shared_experts.up_proj", "model.layers.74.mlp.shared_experts.down_proj", "model.layers.75.mlp.shared_experts.gate_proj", "model.layers.75.mlp.shared_experts.up_proj", "model.layers.75.mlp.shared_experts.down_proj", "model.layers.76.mlp.shared_experts.gate_proj", "model.layers.76.mlp.shared_experts.up_proj", "model.layers.76.mlp.shared_experts.down_proj", "model.layers.77.mlp.shared_experts.gate_proj", "model.layers.77.mlp.shared_experts.up_proj", "model.layers.77.mlp.shared_experts.down_proj", "model.layers.78.mlp.shared_experts.gate_proj", "model.layers.78.mlp.shared_experts.up_proj", "model.layers.78.mlp.shared_experts.down_proj", "model.layers.79.mlp.shared_experts.gate_proj", "model.layers.79.mlp.shared_experts.up_proj", "model.layers.79.mlp.shared_experts.down_proj", "model.layers.80.mlp.shared_experts.gate_proj", "model.layers.80.mlp.shared_experts.up_proj", "model.layers.80.mlp.shared_experts.down_proj", "model.layers.81.mlp.shared_experts.gate_proj", "model.layers.81.mlp.shared_experts.up_proj", "model.layers.81.mlp.shared_experts.down_proj", "model.layers.82.mlp.shared_experts.gate_proj", "model.layers.82.mlp.shared_experts.up_proj", "model.layers.82.mlp.shared_experts.down_proj", "model.layers.83.mlp.shared_experts.gate_proj", "model.layers.83.mlp.shared_experts.up_proj", "model.layers.83.mlp.shared_experts.down_proj", "model.layers.84.mlp.shared_experts.gate_proj", "model.layers.84.mlp.shared_experts.up_proj", "model.layers.84.mlp.shared_experts.down_proj", "model.layers.85.mlp.shared_experts.gate_proj", "model.layers.85.mlp.shared_experts.up_proj", "model.layers.85.mlp.shared_experts.down_proj", "model.layers.86.mlp.shared_experts.gate_proj", "model.layers.86.mlp.shared_experts.up_proj", "model.layers.86.mlp.shared_experts.down_proj", "model.layers.87.mlp.shared_experts.gate_proj", "model.layers.87.mlp.shared_experts.up_proj", "model.layers.87.mlp.shared_experts.down_proj", "model.layers.88.mlp.shared_experts.gate_proj", "model.layers.88.mlp.shared_experts.up_proj", "model.layers.88.mlp.shared_experts.down_proj", "model.layers.89.mlp.shared_experts.gate_proj", "model.layers.89.mlp.shared_experts.up_proj", "model.layers.89.mlp.shared_experts.down_proj", "model.layers.90.mlp.shared_experts.gate_proj", "model.layers.90.mlp.shared_experts.up_proj", "model.layers.90.mlp.shared_experts.down_proj", "model.layers.91.mlp.shared_experts.gate_proj", "model.layers.91.mlp.shared_experts.up_proj", "model.layers.91.mlp.shared_experts.down_proj", "model.layers.92.mlp.shared_experts.gate_proj", "model.layers.92.mlp.shared_experts.up_proj", "model.layers.92.mlp.shared_experts.down_proj", "lm_head" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed", "sparsity_config": {}, "transform_config": {}, "version": "0.12.2.a20251002", "target_scheme_map": { "Linear": { "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": 128, "num_bits": 4, "observer": "minmax", "observer_kwargs": {}, "strategy": "group", "symmetric": true, "type": "int" }, "input_activations": null, "output_activations": null } } }, "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": "4.56.2", "use_cache": true, "use_qk_norm": true, "vocab_size": 151552 }