{ "architectures": [ "Glm5NextForConditionalGeneration" ], "text_config": { "attention_bias": false, "attention_dropout": 0.0, "dtype": "bfloat16", "eos_token_id": [ 154820, 154827, 154829 ], "first_k_dense_replace": 3, "hc_eps": 1e-06, "hc_mult": 4, "hc_sinkhorn_iters": 20, "head_dim": 0, "hidden_act": "silu", "hidden_size": 4096, "index_head_dim": 128, "index_kpool": 4, "index_kpool_always_select_tail": true, "index_kpool_compress": true, "index_n_heads": 32, "index_topk": 2048, "index_share_for_mtp_iteration": true, "indexer_rope_interleave": true, "indexer_types": [ "full", "full", "full", "full" ], "initializer_range": 0.02, "intermediate_size": 12288, "kv_lora_rank": 512, "layer_types": [ "linear_attention", "linear_attention", "linear_attention", "deepseek_sparse_attention" ], "linear_attn_config": { "num_heads": 64, "gate_lower_bound": -5.0, "head_dim": 128, "short_conv_kernel_size": 4, "kda_layers": [ 0, 1, 2 ], "full_attn_layers": [ 3 ] }, "max_position_embeddings": 1048576, "mhc": true, "mla_use_nope": true, "mlp_layer_types": [ "dense", "dense", "dense", "sparse" ], "model_type": "glm5_next_text", "moe_intermediate_size": 2048, "moe_router_dtype": "float32", "n_group": 1, "n_routed_experts": 288, "n_shared_experts": 1, "norm_topk_prob": true, "num_attention_heads": 64, "num_experts_per_tok": 8, "num_hidden_layers": 4, "num_key_value_heads": 64, "num_nextn_predict_layers": 1, "output_router_logits": false, "pad_token_id": 154820, "q_lora_rank": 1536, "qk_head_dim": 256, "qk_nope_head_dim": 256, "qk_rope_head_dim": 0, "rms_norm_eps": 1e-05, "routed_scaling_factor": 2.5, "router_aux_loss_coef": 0.001, "scoring_func": "sigmoid", "swiglu_limit": 10.0, "tie_word_embeddings": false, "topk_group": 1, "topk_method": "noaux_tc", "use_cache": true, "v_head_dim": 256, "vocab_size": 154880 }, "vision_config": { "attention_bias": true, "attention_dropout": 0.0, "depth": 24, "hidden_act": "silu", "hidden_size": 1024, "image_size": 448, "in_channels": 3, "initializer_range": 0.02, "intermediate_size": 4096, "model_type": "glm5_next_vision", "num_heads": 16, "out_hidden_size": 4096, "patch_size": 14, "projection_intermediate_size": 10240, "rms_norm_eps": 1e-05, "spatial_merge_size": 2, "swiglu_limit": 10.0, "temporal_patch_size": 2 }, "image_token_id": 154854, "video_token_id": 154855, "image_start_token_id": 154830, "image_end_token_id": 154831, "video_start_token_id": 154832, "video_end_token_id": 154833, "tie_word_embeddings": false, "model_type": "glm5_next", "transformers_version": "5.16.0", "quantization_config": { "activation_scheme": "dynamic", "fmt": "e4m3", "modules_to_not_convert": [ "attn_mha", "attn_mqa", "dt_bias", "hyper_connection", "lm_head", "mapping_proj", "model.embed_tokens", "model.layers.0.hc_attn_base", "model.layers.0.hc_attn_fn", "model.layers.0.hc_attn_scale", "model.layers.0.hc_ffn_base", "model.layers.0.hc_ffn_fn", "model.layers.0.hc_ffn_scale", "model.layers.0.input_layernorm", "model.layers.0.post_attention_layernorm", "model.layers.0.self_attn.A_log", "model.layers.0.self_attn.b_proj", "model.layers.0.self_attn.dt_bias", "model.layers.0.self_attn.f_a_proj", "model.layers.0.self_attn.f_b_proj", "model.layers.0.self_attn.fused_qkvbfg_a_proj", "model.layers.0.self_attn.g_a_proj", "model.layers.0.self_attn.g_b_proj", "model.layers.0.self_attn.k_conv1d", "model.layers.0.self_attn.k_proj", "model.layers.0.self_attn.o_norm", "model.layers.0.self_attn.o_proj", "model.layers.0.self_attn.q_conv1d", "model.layers.0.self_attn.q_proj", "model.layers.0.self_attn.qkv_proj", "model.layers.0.self_attn.v_conv1d", "model.layers.0.self_attn.v_proj", "model.layers.1.hc_attn_base", "model.layers.1.hc_attn_fn", "model.layers.1.hc_attn_scale", "model.layers.1.hc_ffn_base", "model.layers.1.hc_ffn_fn", "model.layers.1.hc_ffn_scale", "model.layers.1.input_layernorm", "model.layers.1.post_attention_layernorm", "model.layers.1.self_attn.A_log", "model.layers.1.self_attn.b_proj", "model.layers.1.self_attn.dt_bias", "model.layers.1.self_attn.f_a_proj", "model.layers.1.self_attn.f_b_proj", "model.layers.1.self_attn.fused_qkvbfg_a_proj", "model.layers.1.self_attn.g_a_proj", "model.layers.1.self_attn.g_b_proj", "model.layers.1.self_attn.k_conv1d", "model.layers.1.self_attn.k_proj", "model.layers.1.self_attn.o_norm", "model.layers.1.self_attn.o_proj", "model.layers.1.self_attn.q_conv1d", "model.layers.1.self_attn.q_proj", "model.layers.1.self_attn.qkv_proj", "model.layers.1.self_attn.v_conv1d", "model.layers.1.self_attn.v_proj", "model.layers.2.hc_attn_base", "model.layers.2.hc_attn_fn", "model.layers.2.hc_attn_scale", "model.layers.2.hc_ffn_base", "model.layers.2.hc_ffn_fn", "model.layers.2.hc_ffn_scale", "model.layers.2.input_layernorm", "model.layers.2.post_attention_layernorm", "model.layers.2.self_attn.A_log", "model.layers.2.self_attn.b_proj", "model.layers.2.self_attn.dt_bias", "model.layers.2.self_attn.f_a_proj", "model.layers.2.self_attn.f_b_proj", "model.layers.2.self_attn.fused_qkvbfg_a_proj", "model.layers.2.self_attn.g_a_proj", "model.layers.2.self_attn.g_b_proj", "model.layers.2.self_attn.k_conv1d", "model.layers.2.self_attn.k_proj", "model.layers.2.self_attn.o_norm", "model.layers.2.self_attn.o_proj", "model.layers.2.self_attn.q_conv1d", "model.layers.2.self_attn.q_proj", "model.layers.2.self_attn.qkv_proj", "model.layers.2.self_attn.v_conv1d", "model.layers.2.self_attn.v_proj", "model.layers.3.hc_attn_base", "model.layers.3.hc_attn_fn", "model.layers.3.hc_attn_scale", "model.layers.3.hc_ffn_base", "model.layers.3.hc_ffn_fn", "model.layers.3.hc_ffn_scale", "model.layers.3.input_layernorm", "model.layers.3.mlp.gate", "model.layers.3.mlp.gate.e_score_correction_bias", "model.layers.3.post_attention_layernorm", "model.layers.3.self_attn.indexer.index_kpool_compress_ape", "model.layers.3.self_attn.indexer.index_kpool_compress_gate", "model.layers.3.self_attn.indexer.k_norm", "model.layers.3.self_attn.indexer.k_norm.bias", "model.layers.3.self_attn.indexer.weights_proj", "model.layers.3.self_attn.indexer.wk", "model.layers.3.self_attn.indexer.wq_b", "model.layers.3.self_attn.kv_a_layernorm", "model.layers.3.self_attn.kv_b_proj", "model.layers.3.self_attn.q_a_layernorm", "model.layers.4.eh_proj", "model.layers.4.enorm", "model.layers.4.hnorm", "model.layers.4.input_layernorm", "model.layers.4.mlp.gate", "model.layers.4.mlp.gate.e_score_correction_bias", "model.layers.4.post_attention_layernorm", "model.layers.4.self_attn.indexer.index_kpool_compress_ape", "model.layers.4.self_attn.indexer.index_kpool_compress_gate", "model.layers.4.self_attn.indexer.k_norm", "model.layers.4.self_attn.indexer.k_norm.bias", "model.layers.4.self_attn.indexer.weights_proj", "model.layers.4.self_attn.indexer.wk", "model.layers.4.self_attn.indexer.wq_b", "model.layers.4.self_attn.kv_a_layernorm", "model.layers.4.self_attn.kv_b_proj", "model.layers.4.self_attn.q_a_layernorm", "model.layers.4.shared_head.norm", "model.norm", "model.visual", "router", "visual", "visual.blocks.0.attn.k_norm", "visual.blocks.0.attn.proj", "visual.blocks.0.attn.proj.bias", "visual.blocks.0.attn.q_norm", "visual.blocks.0.attn.qkv", "visual.blocks.0.attn.qkv.bias", "visual.blocks.0.mlp.down_proj", "visual.blocks.0.mlp.down_proj.bias", "visual.blocks.0.mlp.gate_proj", "visual.blocks.0.mlp.gate_proj.bias", "visual.blocks.0.mlp.up_proj", "visual.blocks.0.mlp.up_proj.bias", "visual.blocks.0.norm1", "visual.blocks.0.norm2", "visual.blocks.1.attn.k_norm", "visual.blocks.1.attn.proj", "visual.blocks.1.attn.proj.bias", "visual.blocks.1.attn.q_norm", "visual.blocks.1.attn.qkv", "visual.blocks.1.attn.qkv.bias", "visual.blocks.1.mlp.down_proj", "visual.blocks.1.mlp.down_proj.bias", "visual.blocks.1.mlp.gate_proj", "visual.blocks.1.mlp.gate_proj.bias", "visual.blocks.1.mlp.up_proj", "visual.blocks.1.mlp.up_proj.bias", "visual.blocks.1.norm1", "visual.blocks.1.norm2", "visual.blocks.10.attn.k_norm", "visual.blocks.10.attn.proj", "visual.blocks.10.attn.proj.bias", "visual.blocks.10.attn.q_norm", "visual.blocks.10.attn.qkv", "visual.blocks.10.attn.qkv.bias", "visual.blocks.10.mlp.down_proj", "visual.blocks.10.mlp.down_proj.bias", "visual.blocks.10.mlp.gate_proj", "visual.blocks.10.mlp.gate_proj.bias", "visual.blocks.10.mlp.up_proj", "visual.blocks.10.mlp.up_proj.bias", "visual.blocks.10.norm1", "visual.blocks.10.norm2", "visual.blocks.11.attn.k_norm", "visual.blocks.11.attn.proj", "visual.blocks.11.attn.proj.bias", "visual.blocks.11.attn.q_norm", "visual.blocks.11.attn.qkv", "visual.blocks.11.attn.qkv.bias", "visual.blocks.11.mlp.down_proj", "visual.blocks.11.mlp.down_proj.bias", "visual.blocks.11.mlp.gate_proj", "visual.blocks.11.mlp.gate_proj.bias", "visual.blocks.11.mlp.up_proj", "visual.blocks.11.mlp.up_proj.bias", "visual.blocks.11.norm1", "visual.blocks.11.norm2", "visual.blocks.12.attn.k_norm", "visual.blocks.12.attn.proj", "visual.blocks.12.attn.proj.bias", "visual.blocks.12.attn.q_norm", "visual.blocks.12.attn.qkv", "visual.blocks.12.attn.qkv.bias", "visual.blocks.12.mlp.down_proj", "visual.blocks.12.mlp.down_proj.bias", "visual.blocks.12.mlp.gate_proj", "visual.blocks.12.mlp.gate_proj.bias", "visual.blocks.12.mlp.up_proj", "visual.blocks.12.mlp.up_proj.bias", "visual.blocks.12.norm1", "visual.blocks.12.norm2", "visual.blocks.13.attn.k_norm", "visual.blocks.13.attn.proj", "visual.blocks.13.attn.proj.bias", "visual.blocks.13.attn.q_norm", "visual.blocks.13.attn.qkv", "visual.blocks.13.attn.qkv.bias", "visual.blocks.13.mlp.down_proj", "visual.blocks.13.mlp.down_proj.bias", "visual.blocks.13.mlp.gate_proj", "visual.blocks.13.mlp.gate_proj.bias", "visual.blocks.13.mlp.up_proj", "visual.blocks.13.mlp.up_proj.bias", "visual.blocks.13.norm1", "visual.blocks.13.norm2", "visual.blocks.14.attn.k_norm", "visual.blocks.14.attn.proj", "visual.blocks.14.attn.proj.bias", "visual.blocks.14.attn.q_norm", "visual.blocks.14.attn.qkv", "visual.blocks.14.attn.qkv.bias", "visual.blocks.14.mlp.down_proj", "visual.blocks.14.mlp.down_proj.bias", "visual.blocks.14.mlp.gate_proj", "visual.blocks.14.mlp.gate_proj.bias", "visual.blocks.14.mlp.up_proj", "visual.blocks.14.mlp.up_proj.bias", "visual.blocks.14.norm1", "visual.blocks.14.norm2", "visual.blocks.15.attn.k_norm", "visual.blocks.15.attn.proj", "visual.blocks.15.attn.proj.bias", "visual.blocks.15.attn.q_norm", "visual.blocks.15.attn.qkv", "visual.blocks.15.attn.qkv.bias", "visual.blocks.15.mlp.down_proj", "visual.blocks.15.mlp.down_proj.bias", "visual.blocks.15.mlp.gate_proj", "visual.blocks.15.mlp.gate_proj.bias", "visual.blocks.15.mlp.up_proj", "visual.blocks.15.mlp.up_proj.bias", "visual.blocks.15.norm1", "visual.blocks.15.norm2", "visual.blocks.16.attn.k_norm", "visual.blocks.16.attn.proj", "visual.blocks.16.attn.proj.bias", "visual.blocks.16.attn.q_norm", "visual.blocks.16.attn.qkv", "visual.blocks.16.attn.qkv.bias", "visual.blocks.16.mlp.down_proj", "visual.blocks.16.mlp.down_proj.bias", "visual.blocks.16.mlp.gate_proj", "visual.blocks.16.mlp.gate_proj.bias", "visual.blocks.16.mlp.up_proj", "visual.blocks.16.mlp.up_proj.bias", "visual.blocks.16.norm1", "visual.blocks.16.norm2", "visual.blocks.17.attn.k_norm", "visual.blocks.17.attn.proj", "visual.blocks.17.attn.proj.bias", "visual.blocks.17.attn.q_norm", "visual.blocks.17.attn.qkv", "visual.blocks.17.attn.qkv.bias", "visual.blocks.17.mlp.down_proj", "visual.blocks.17.mlp.down_proj.bias", "visual.blocks.17.mlp.gate_proj", "visual.blocks.17.mlp.gate_proj.bias", "visual.blocks.17.mlp.up_proj", "visual.blocks.17.mlp.up_proj.bias", "visual.blocks.17.norm1", "visual.blocks.17.norm2", "visual.blocks.18.attn.k_norm", "visual.blocks.18.attn.proj", "visual.blocks.18.attn.proj.bias", "visual.blocks.18.attn.q_norm", "visual.blocks.18.attn.qkv", "visual.blocks.18.attn.qkv.bias", "visual.blocks.18.mlp.down_proj", "visual.blocks.18.mlp.down_proj.bias", "visual.blocks.18.mlp.gate_proj", "visual.blocks.18.mlp.gate_proj.bias", "visual.blocks.18.mlp.up_proj", "visual.blocks.18.mlp.up_proj.bias", "visual.blocks.18.norm1", "visual.blocks.18.norm2", "visual.blocks.19.attn.k_norm", "visual.blocks.19.attn.proj", "visual.blocks.19.attn.proj.bias", "visual.blocks.19.attn.q_norm", "visual.blocks.19.attn.qkv", "visual.blocks.19.attn.qkv.bias", "visual.blocks.19.mlp.down_proj", "visual.blocks.19.mlp.down_proj.bias", "visual.blocks.19.mlp.gate_proj", "visual.blocks.19.mlp.gate_proj.bias", "visual.blocks.19.mlp.up_proj", "visual.blocks.19.mlp.up_proj.bias", "visual.blocks.19.norm1", "visual.blocks.19.norm2", "visual.blocks.2.attn.k_norm", "visual.blocks.2.attn.proj", "visual.blocks.2.attn.proj.bias", "visual.blocks.2.attn.q_norm", "visual.blocks.2.attn.qkv", "visual.blocks.2.attn.qkv.bias", "visual.blocks.2.mlp.down_proj", "visual.blocks.2.mlp.down_proj.bias", "visual.blocks.2.mlp.gate_proj", "visual.blocks.2.mlp.gate_proj.bias", "visual.blocks.2.mlp.up_proj", "visual.blocks.2.mlp.up_proj.bias", "visual.blocks.2.norm1", "visual.blocks.2.norm2", "visual.blocks.20.attn.k_norm", "visual.blocks.20.attn.proj", "visual.blocks.20.attn.proj.bias", "visual.blocks.20.attn.q_norm", "visual.blocks.20.attn.qkv", "visual.blocks.20.attn.qkv.bias", "visual.blocks.20.mlp.down_proj", "visual.blocks.20.mlp.down_proj.bias", "visual.blocks.20.mlp.gate_proj", "visual.blocks.20.mlp.gate_proj.bias", "visual.blocks.20.mlp.up_proj", "visual.blocks.20.mlp.up_proj.bias", "visual.blocks.20.norm1", "visual.blocks.20.norm2", "visual.blocks.21.attn.k_norm", "visual.blocks.21.attn.proj", "visual.blocks.21.attn.proj.bias", "visual.blocks.21.attn.q_norm", "visual.blocks.21.attn.qkv", "visual.blocks.21.attn.qkv.bias", "visual.blocks.21.mlp.down_proj", "visual.blocks.21.mlp.down_proj.bias", "visual.blocks.21.mlp.gate_proj", "visual.blocks.21.mlp.gate_proj.bias", "visual.blocks.21.mlp.up_proj", "visual.blocks.21.mlp.up_proj.bias", "visual.blocks.21.norm1", "visual.blocks.21.norm2", "visual.blocks.22.attn.k_norm", "visual.blocks.22.attn.proj", "visual.blocks.22.attn.proj.bias", "visual.blocks.22.attn.q_norm", "visual.blocks.22.attn.qkv", "visual.blocks.22.attn.qkv.bias", "visual.blocks.22.mlp.down_proj", "visual.blocks.22.mlp.down_proj.bias", "visual.blocks.22.mlp.gate_proj", "visual.blocks.22.mlp.gate_proj.bias", "visual.blocks.22.mlp.up_proj", "visual.blocks.22.mlp.up_proj.bias", "visual.blocks.22.norm1", "visual.blocks.22.norm2", "visual.blocks.23.attn.k_norm", "visual.blocks.23.attn.proj", "visual.blocks.23.attn.proj.bias", "visual.blocks.23.attn.q_norm", "visual.blocks.23.attn.qkv", "visual.blocks.23.attn.qkv.bias", "visual.blocks.23.mlp.down_proj", "visual.blocks.23.mlp.down_proj.bias", "visual.blocks.23.mlp.gate_proj", "visual.blocks.23.mlp.gate_proj.bias", "visual.blocks.23.mlp.up_proj", "visual.blocks.23.mlp.up_proj.bias", "visual.blocks.23.norm1", "visual.blocks.23.norm2", "visual.blocks.3.attn.k_norm", "visual.blocks.3.attn.proj", "visual.blocks.3.attn.proj.bias", "visual.blocks.3.attn.q_norm", "visual.blocks.3.attn.qkv", "visual.blocks.3.attn.qkv.bias", "visual.blocks.3.mlp.down_proj", "visual.blocks.3.mlp.down_proj.bias", "visual.blocks.3.mlp.gate_proj", "visual.blocks.3.mlp.gate_proj.bias", "visual.blocks.3.mlp.up_proj", "visual.blocks.3.mlp.up_proj.bias", "visual.blocks.3.norm1", "visual.blocks.3.norm2", "visual.blocks.4.attn.k_norm", "visual.blocks.4.attn.proj", "visual.blocks.4.attn.proj.bias", "visual.blocks.4.attn.q_norm", "visual.blocks.4.attn.qkv", "visual.blocks.4.attn.qkv.bias", "visual.blocks.4.mlp.down_proj", "visual.blocks.4.mlp.down_proj.bias", "visual.blocks.4.mlp.gate_proj", "visual.blocks.4.mlp.gate_proj.bias", "visual.blocks.4.mlp.up_proj", "visual.blocks.4.mlp.up_proj.bias", "visual.blocks.4.norm1", "visual.blocks.4.norm2", "visual.blocks.5.attn.k_norm", "visual.blocks.5.attn.proj", "visual.blocks.5.attn.proj.bias", "visual.blocks.5.attn.q_norm", "visual.blocks.5.attn.qkv", "visual.blocks.5.attn.qkv.bias", "visual.blocks.5.mlp.down_proj", "visual.blocks.5.mlp.down_proj.bias", "visual.blocks.5.mlp.gate_proj", "visual.blocks.5.mlp.gate_proj.bias", "visual.blocks.5.mlp.up_proj", "visual.blocks.5.mlp.up_proj.bias", "visual.blocks.5.norm1", "visual.blocks.5.norm2", "visual.blocks.6.attn.k_norm", "visual.blocks.6.attn.proj", "visual.blocks.6.attn.proj.bias", "visual.blocks.6.attn.q_norm", "visual.blocks.6.attn.qkv", "visual.blocks.6.attn.qkv.bias", "visual.blocks.6.mlp.down_proj", "visual.blocks.6.mlp.down_proj.bias", "visual.blocks.6.mlp.gate_proj", "visual.blocks.6.mlp.gate_proj.bias", "visual.blocks.6.mlp.up_proj", "visual.blocks.6.mlp.up_proj.bias", "visual.blocks.6.norm1", "visual.blocks.6.norm2", "visual.blocks.7.attn.k_norm", "visual.blocks.7.attn.proj", "visual.blocks.7.attn.proj.bias", "visual.blocks.7.attn.q_norm", "visual.blocks.7.attn.qkv", "visual.blocks.7.attn.qkv.bias", "visual.blocks.7.mlp.down_proj", "visual.blocks.7.mlp.down_proj.bias", "visual.blocks.7.mlp.gate_proj", "visual.blocks.7.mlp.gate_proj.bias", "visual.blocks.7.mlp.up_proj", "visual.blocks.7.mlp.up_proj.bias", "visual.blocks.7.norm1", "visual.blocks.7.norm2", "visual.blocks.8.attn.k_norm", "visual.blocks.8.attn.proj", "visual.blocks.8.attn.proj.bias", "visual.blocks.8.attn.q_norm", "visual.blocks.8.attn.qkv", "visual.blocks.8.attn.qkv.bias", "visual.blocks.8.mlp.down_proj", "visual.blocks.8.mlp.down_proj.bias", "visual.blocks.8.mlp.gate_proj", "visual.blocks.8.mlp.gate_proj.bias", "visual.blocks.8.mlp.up_proj", "visual.blocks.8.mlp.up_proj.bias", "visual.blocks.8.norm1", "visual.blocks.8.norm2", "visual.blocks.9.attn.k_norm", "visual.blocks.9.attn.proj", "visual.blocks.9.attn.proj.bias", "visual.blocks.9.attn.q_norm", "visual.blocks.9.attn.qkv", "visual.blocks.9.attn.qkv.bias", "visual.blocks.9.mlp.down_proj", "visual.blocks.9.mlp.down_proj.bias", "visual.blocks.9.mlp.gate_proj", "visual.blocks.9.mlp.gate_proj.bias", "visual.blocks.9.mlp.up_proj", "visual.blocks.9.mlp.up_proj.bias", "visual.blocks.9.norm1", "visual.blocks.9.norm2", "visual.downsample", "visual.downsample.bias", "visual.merger.down_proj", "visual.merger.gate_proj", "visual.merger.post_projection_norm", "visual.merger.post_projection_norm.bias", "visual.merger.proj", "visual.merger.up_proj", "visual.patch_embed.proj", "visual.patch_embed.proj.bias", "visual.post_layernorm", "weights_proj" ], "quant_method": "fp8", "weight_block_size": [ 128, 128 ] } }