{ "vocab_size": 154880, "max_position_embeddings": 202752, "hidden_size": 6144, "intermediate_size": 12288, "num_hidden_layers": 78, "mlp_layer_types": [ "dense", "dense", "dense", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse" ], "moe_intermediate_size": 2048, "num_attention_heads": 64, "n_shared_experts": 1, "n_routed_experts": 256, "routed_scaling_factor": 2.5, "kv_lora_rank": 512, "q_lora_rank": 2048, "qk_rope_head_dim": 64, "v_head_dim": 256, "qk_nope_head_dim": 192, "qk_head_dim": 256, "head_dim": 64, "n_group": 1, "topk_group": 1, "num_experts_per_tok": 8, "norm_topk_prob": true, "rope_interleave": true, "num_key_value_heads": 64, "hidden_act": "silu", "initializer_range": 0.02, "index_topk": 2048, "rms_norm_eps": 1e-05, "use_cache": true, "attention_bias": false, "attention_dropout": 0.0, "rope_parameters": { "rope_theta": 1000000, "rope_type": "default" }, "pad_token_id": 154820, "bos_token_id": 0, "eos_token_id": [ 154820, 154827, 154829 ], "tie_word_embeddings": false, "return_dict": true, "output_hidden_states": false, "dtype": "bfloat16", "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "architectures": [ "GlmMoeDsaForCausalLM" ], "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "_name_or_path": "zai-org/GLM-5", "transformers_version": "5.2.0.dev0", "ep_size": 1, "first_k_dense_replace": 3, "index_head_dim": 128, "index_n_heads": 32, "indexer_rope_interleave": true, "moe_layer_freq": 1, "model_type": "glm_moe_dsa", "num_nextn_predict_layers": 1, "pretraining_tp": 1, "scoring_func": "sigmoid", "topk_method": "noaux_tc", "output_attentions": false, "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": [ "lm_head", "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.eh_proj*", "model.layers.78.enorm*", "model.layers.78.hnorm*", "model.layers.78.input_layernorm*", "model.layers.78.mlp*", "model.layers.78.post_attention_layernorm*", "model.layers.78.self_attn*", "model.layers.78.shared_head*", "model.layers.8.self_attn*", "model.layers.9.self_attn*" ], "quant_algo": "NVFP4", "kv_cache_scheme": { "dynamic": false, "num_bits": 8, "type": "float" }, "producer": { "name": "modelopt", "version": "0.39.0.dev290+gf9d9a71de.d20260214" }, "quant_method": "modelopt" } }