{ "architectures": [ "Glm4MoeLiteForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "pad_token_id": 154820, "eos_token_id": [ 154820, 154827, 154829 ], "hidden_act": "silu", "hidden_size": 2048, "intermediate_size": 10240, "max_position_embeddings": 202752, "model_type": "glm4_moe_lite", "moe_intermediate_size": 1536, "topk_method": "noaux_tc", "norm_topk_prob": true, "num_attention_heads": 20, "n_group": 1, "topk_group": 1, "n_routed_experts": 64, "n_shared_experts": 1, "routed_scaling_factor": 1.8, "num_experts_per_tok": 4, "first_k_dense_replace": 1, "num_hidden_layers": 47, "num_key_value_heads": 20, "num_nextn_predict_layers": 1, "partial_rotary_factor": 1.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 1000000, "tie_word_embeddings": false, "dtype": "bfloat16", "transformers_version": "5.0.0rc0", "q_lora_rank": 768, "kv_lora_rank": 512, "qk_nope_head_dim": 192, "qk_rope_head_dim": 64, "v_head_dim": 256, "vocab_size": 154880, "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": [ "model.layers.1.mlp.experts", "model.layers.2.mlp.experts", "model.layers.3.mlp.experts", "model.layers.4.mlp.experts", "model.layers.5.mlp.experts", "model.layers.6.mlp.experts", "model.layers.7.mlp.experts", "model.layers.8.mlp.experts", "model.layers.9.mlp.experts", "model.layers.10.mlp.experts", "model.layers.11.mlp.experts", "model.layers.12.mlp.experts", "model.layers.13.mlp.experts", "model.layers.14.mlp.experts", "model.layers.15.mlp.experts", "model.layers.16.mlp.experts", "model.layers.17.mlp.experts", "model.layers.18.mlp.experts", "model.layers.19.mlp.experts", "model.layers.20.mlp.experts", "model.layers.21.mlp.experts", "model.layers.22.mlp.experts", "model.layers.23.mlp.experts", "model.layers.24.mlp.experts", "model.layers.25.mlp.experts", "model.layers.26.mlp.experts", "model.layers.27.mlp.experts", "model.layers.28.mlp.experts", "model.layers.29.mlp.experts", "model.layers.30.mlp.experts", "model.layers.31.mlp.experts", "model.layers.32.mlp.experts", "model.layers.33.mlp.experts", "model.layers.34.mlp.experts", "model.layers.35.mlp.experts", "model.layers.36.mlp.experts", "model.layers.37.mlp.experts", "model.layers.38.mlp.experts", "model.layers.39.mlp.experts", "model.layers.40.mlp.experts", "model.layers.41.mlp.experts", "model.layers.42.mlp.experts", "model.layers.43.mlp.experts", "model.layers.44.mlp.experts", "model.layers.45.mlp.experts", "model.layers.46.mlp.experts" ] } }, "ignore": [ "lm_head", "model.embed_tokens", "model.layers.*.mlp.down_proj", "model.layers.*.mlp.gate", "model.layers.*.mlp.gate_proj", "model.layers.*.mlp.shared_experts.down_proj", "model.layers.*.mlp.shared_experts.gate_proj", "model.layers.*.mlp.shared_experts.up_proj", "model.layers.*.mlp.up_proj", "model.layers.*.self_attn.kv_a_proj_with_mqa", "model.layers.*.self_attn.kv_b_proj", "model.layers.*.self_attn.o_proj", "model.layers.*.self_attn.q_a_proj", "model.layers.*.self_attn.q_b_proj" ], "quant_algo": "MIXED_PRECISION", "producer": { "name": "modelopt", "version": "0.47.0rc1.dev129+g333ace1bc" }, "quant_method": "modelopt", "quantized_layers": { "model.layers.1.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.10.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.11.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.12.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.13.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.14.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.15.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.16.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.17.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.18.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.19.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.2.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.20.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.21.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.22.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.23.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.24.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.25.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.26.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.27.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.28.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.29.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.3.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.30.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.31.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.32.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.33.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.34.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.35.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.36.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.37.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.38.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.39.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.4.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.40.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.41.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.42.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.43.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.44.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.45.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.46.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.5.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.6.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.7.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.8.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.9.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 } } } }