{ "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": 128, "index_head_dim": 128, "index_kpool": 4, "index_kpool_always_select_tail": true, "index_kpool_compress": true, "index_n_heads": 32, "index_topk": 128, "index_share_for_mtp_iteration": true, "indexer_rope_interleave": true, "indexer_types": [ "full", "full", "full", "full", "full", "full", "full", "full" ], "initializer_range": 0.02, "intermediate_size": 128, "kv_lora_rank": 256, "layer_types": [ "linear_attention", "linear_attention", "linear_attention", "indexed_attention", "linear_attention", "linear_attention", "linear_attention", "indexed_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, 4, 5, 6 ], "full_attn_layers": [ 3, 7 ] }, "max_position_embeddings": 1048576, "mhc": true, "mla_use_nope": true, "mlp_layer_types": [ "dense", "dense", "dense", "sparse", "sparse", "sparse", "sparse", "sparse" ], "model_type": "glm5_next_text", "moe_intermediate_size": 128, "moe_router_dtype": "float32", "n_group": 1, "n_routed_experts": 32, "n_shared_experts": 1, "norm_topk_prob": true, "num_attention_heads": 64, "num_experts_per_tok": 8, "num_hidden_layers": 8, "num_key_value_heads": 64, "num_nextn_predict_layers": 1, "output_router_logits": false, "pad_token_id": 154820, "q_lora_rank": 128, "qk_head_dim": 256, "qk_nope_head_dim": 32, "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, "linear_head_dim": 128 }, "vision_config": { "attention_bias": true, "attention_dropout": 0.0, "depth": 2, "hidden_act": "silu", "hidden_size": 128, "image_size": 28, "in_channels": 3, "initializer_range": 0.02, "intermediate_size": 256, "model_type": "glm5_next_vision", "num_heads": 4, "out_hidden_size": 128, "patch_size": 14, "projection_intermediate_size": 64, "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": [ "lm_head", "model.language_model.embed_tokens", "model.language_model.layers.0.self_attn.b_proj", "model.language_model.layers.0.self_attn.forget_gate.f_a_proj", "model.language_model.layers.0.self_attn.forget_gate.f_b_proj", "model.language_model.layers.0.self_attn.g_a_proj", "model.language_model.layers.0.self_attn.g_b_proj", "model.language_model.layers.0.self_attn.k_proj", "model.language_model.layers.0.self_attn.o_proj", "model.language_model.layers.0.self_attn.q_proj", "model.language_model.layers.0.self_attn.v_proj", "model.language_model.layers.1.self_attn.b_proj", "model.language_model.layers.1.self_attn.forget_gate.f_a_proj", "model.language_model.layers.1.self_attn.forget_gate.f_b_proj", "model.language_model.layers.1.self_attn.g_a_proj", "model.language_model.layers.1.self_attn.g_b_proj", "model.language_model.layers.1.self_attn.k_proj", "model.language_model.layers.1.self_attn.o_proj", "model.language_model.layers.1.self_attn.q_proj", "model.language_model.layers.1.self_attn.v_proj", "model.language_model.layers.2.self_attn.b_proj", "model.language_model.layers.2.self_attn.forget_gate.f_a_proj", "model.language_model.layers.2.self_attn.forget_gate.f_b_proj", "model.language_model.layers.2.self_attn.g_a_proj", "model.language_model.layers.2.self_attn.g_b_proj", "model.language_model.layers.2.self_attn.k_proj", "model.language_model.layers.2.self_attn.o_proj", "model.language_model.layers.2.self_attn.q_proj", "model.language_model.layers.2.self_attn.v_proj", "model.language_model.layers.3.self_attn.indexer.weights_proj", "model.language_model.layers.3.self_attn.indexer.wk", "model.language_model.layers.3.self_attn.indexer.wq_b", "model.language_model.layers.3.self_attn.kv_b_proj", "model.language_model.layers.4.self_attn.b_proj", "model.language_model.layers.4.self_attn.forget_gate.f_a_proj", "model.language_model.layers.4.self_attn.forget_gate.f_b_proj", "model.language_model.layers.4.self_attn.g_a_proj", "model.language_model.layers.4.self_attn.g_b_proj", "model.language_model.layers.4.self_attn.k_proj", "model.language_model.layers.4.self_attn.o_proj", "model.language_model.layers.4.self_attn.q_proj", "model.language_model.layers.4.self_attn.v_proj", "model.language_model.layers.5.self_attn.b_proj", "model.language_model.layers.5.self_attn.forget_gate.f_a_proj", "model.language_model.layers.5.self_attn.forget_gate.f_b_proj", "model.language_model.layers.5.self_attn.g_a_proj", "model.language_model.layers.5.self_attn.g_b_proj", "model.language_model.layers.5.self_attn.k_proj", "model.language_model.layers.5.self_attn.o_proj", "model.language_model.layers.5.self_attn.q_proj", "model.language_model.layers.5.self_attn.v_proj", "model.language_model.layers.6.self_attn.b_proj", "model.language_model.layers.6.self_attn.forget_gate.f_a_proj", "model.language_model.layers.6.self_attn.forget_gate.f_b_proj", "model.language_model.layers.6.self_attn.g_a_proj", "model.language_model.layers.6.self_attn.g_b_proj", "model.language_model.layers.6.self_attn.k_proj", "model.language_model.layers.6.self_attn.o_proj", "model.language_model.layers.6.self_attn.q_proj", "model.language_model.layers.6.self_attn.v_proj", "model.language_model.layers.7.self_attn.indexer.weights_proj", "model.language_model.layers.7.self_attn.indexer.wk", "model.language_model.layers.7.self_attn.indexer.wq_b", "model.language_model.layers.7.self_attn.kv_b_proj", "model.visual", "model.visual.blocks.0.attn.proj", "model.visual.blocks.0.attn.qkv", "model.visual.blocks.0.mlp.down_proj", "model.visual.blocks.0.mlp.gate_proj", "model.visual.blocks.0.mlp.up_proj", "model.visual.blocks.1.attn.proj", "model.visual.blocks.1.attn.qkv", "model.visual.blocks.1.mlp.down_proj", "model.visual.blocks.1.mlp.gate_proj", "model.visual.blocks.1.mlp.up_proj", "model.visual.merger.down_proj", "model.visual.merger.gate_proj", "model.visual.merger.proj", "model.visual.merger.up_proj" ], "quant_method": "fp8", "weight_block_size": [ 32, 32 ] } }