{ "architectures": [ "LagunaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_laguna.LagunaConfig", "AutoModelForCausalLM": "modeling_laguna.LagunaForCausalLM" }, "bos_token_id": 2, "decoder_sparse_step": 1, "dtype": "bfloat16", "eos_token_id": [ 2, 24 ], "gating": "per-head", "gating_types": [ "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head", "per_head" ], "head_dim": 128, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 12288, "layer_types": [ "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention" ], "max_position_embeddings": 1048576, "mlp_layer_types": [ "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" ], "mlp_only_layers": [ 0 ], "model_type": "laguna", "moe_apply_router_weight_on_input": false, "moe_intermediate_size": 1024, "moe_routed_scaling_factor": 2.5, "moe_router_logit_softcapping": 0.0, "norm_topk_prob": true, "num_attention_heads": 48, "num_attention_heads_per_layer": [ 48, 72, 72, 72, 48, 72, 72, 72, 48, 72, 72, 72, 48, 72, 72, 72, 48, 72, 72, 72, 48, 72, 72, 72, 48, 72, 72, 72, 48, 72, 72, 72, 48, 72, 72, 72, 48, 72, 72, 72, 48, 72, 72, 72, 48, 72, 72, 72 ], "num_experts": 256, "num_experts_per_tok": 10, "num_hidden_layers": 48, "num_key_value_heads": 8, "output_router_logits": false, "pad_token_id": 9, "partial_rotary_factor": null, "qkv_bias": false, "quantization_config": { "config_groups": { "group_0": { "format": "nvfp4-pack-quantized", "input_activations": { "actorder": null, "block_structure": null, "dynamic": "local", "group_size": 16, "num_bits": 4, "observer": "reject_minmax", "observer_kwargs": { "reject_factor": 100.0 }, "scale_dtype": "torch.float8_e4m3fn", "strategy": "tensor_group", "symmetric": true, "type": "float", "zp_dtype": null }, "output_activations": null, "targets": [ "re:.*\\.mlp\\.experts\\.[0-9]+\\.(gate_proj|up_proj|down_proj)$" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": 16, "num_bits": 4, "observer": "minmax", "observer_kwargs": {}, "scale_dtype": "torch.float8_e4m3fn", "strategy": "tensor_group", "symmetric": true, "type": "float", "zp_dtype": null } } }, "format": "nvfp4-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.self_attn.g_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.self_attn.g_proj", "model.layers.1.mlp.shared_expert.gate_proj", "model.layers.1.mlp.shared_expert.up_proj", "model.layers.1.mlp.shared_expert.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.self_attn.g_proj", "model.layers.2.mlp.shared_expert.gate_proj", "model.layers.2.mlp.shared_expert.up_proj", "model.layers.2.mlp.shared_expert.down_proj", "model.layers.3.self_attn.q_proj", "model.layers.3.self_attn.k_proj", "model.layers.3.self_attn.v_proj", "model.layers.3.self_attn.o_proj", "model.layers.3.self_attn.g_proj", "model.layers.3.mlp.shared_expert.gate_proj", "model.layers.3.mlp.shared_expert.up_proj", "model.layers.3.mlp.shared_expert.down_proj", "model.layers.4.self_attn.q_proj", "model.layers.4.self_attn.k_proj", "model.layers.4.self_attn.v_proj", "model.layers.4.self_attn.o_proj", "model.layers.4.self_attn.g_proj", "model.layers.4.mlp.shared_expert.gate_proj", "model.layers.4.mlp.shared_expert.up_proj", "model.layers.4.mlp.shared_expert.down_proj", "model.layers.5.self_attn.q_proj", "model.layers.5.self_attn.k_proj", "model.layers.5.self_attn.v_proj", "model.layers.5.self_attn.o_proj", "model.layers.5.self_attn.g_proj", "model.layers.5.mlp.shared_expert.gate_proj", "model.layers.5.mlp.shared_expert.up_proj", "model.layers.5.mlp.shared_expert.down_proj", "model.layers.6.self_attn.q_proj", "model.layers.6.self_attn.k_proj", "model.layers.6.self_attn.v_proj", "model.layers.6.self_attn.o_proj", "model.layers.6.self_attn.g_proj", "model.layers.6.mlp.shared_expert.gate_proj", "model.layers.6.mlp.shared_expert.up_proj", "model.layers.6.mlp.shared_expert.down_proj", "model.layers.7.self_attn.q_proj", "model.layers.7.self_attn.k_proj", "model.layers.7.self_attn.v_proj", "model.layers.7.self_attn.o_proj", "model.layers.7.self_attn.g_proj", "model.layers.7.mlp.shared_expert.gate_proj", "model.layers.7.mlp.shared_expert.up_proj", "model.layers.7.mlp.shared_expert.down_proj", "model.layers.8.self_attn.q_proj", "model.layers.8.self_attn.k_proj", "model.layers.8.self_attn.v_proj", "model.layers.8.self_attn.o_proj", "model.layers.8.self_attn.g_proj", "model.layers.8.mlp.shared_expert.gate_proj", "model.layers.8.mlp.shared_expert.up_proj", "model.layers.8.mlp.shared_expert.down_proj", "model.layers.9.self_attn.q_proj", "model.layers.9.self_attn.k_proj", "model.layers.9.self_attn.v_proj", "model.layers.9.self_attn.o_proj", "model.layers.9.self_attn.g_proj", "model.layers.9.mlp.shared_expert.gate_proj", "model.layers.9.mlp.shared_expert.up_proj", "model.layers.9.mlp.shared_expert.down_proj", "model.layers.10.self_attn.q_proj", "model.layers.10.self_attn.k_proj", "model.layers.10.self_attn.v_proj", "model.layers.10.self_attn.o_proj", "model.layers.10.self_attn.g_proj", "model.layers.10.mlp.shared_expert.gate_proj", "model.layers.10.mlp.shared_expert.up_proj", "model.layers.10.mlp.shared_expert.down_proj", "model.layers.11.self_attn.q_proj", "model.layers.11.self_attn.k_proj", "model.layers.11.self_attn.v_proj", "model.layers.11.self_attn.o_proj", "model.layers.11.self_attn.g_proj", "model.layers.11.mlp.shared_expert.gate_proj", "model.layers.11.mlp.shared_expert.up_proj", "model.layers.11.mlp.shared_expert.down_proj", "model.layers.12.self_attn.q_proj", "model.layers.12.self_attn.k_proj", "model.layers.12.self_attn.v_proj", "model.layers.12.self_attn.o_proj", "model.layers.12.self_attn.g_proj", "model.layers.12.mlp.shared_expert.gate_proj", "model.layers.12.mlp.shared_expert.up_proj", "model.layers.12.mlp.shared_expert.down_proj", "model.layers.13.self_attn.q_proj", "model.layers.13.self_attn.k_proj", "model.layers.13.self_attn.v_proj", "model.layers.13.self_attn.o_proj", "model.layers.13.self_attn.g_proj", "model.layers.13.mlp.shared_expert.gate_proj", "model.layers.13.mlp.shared_expert.up_proj", "model.layers.13.mlp.shared_expert.down_proj", "model.layers.14.self_attn.q_proj", "model.layers.14.self_attn.k_proj", "model.layers.14.self_attn.v_proj", "model.layers.14.self_attn.o_proj", "model.layers.14.self_attn.g_proj", "model.layers.14.mlp.shared_expert.gate_proj", "model.layers.14.mlp.shared_expert.up_proj", "model.layers.14.mlp.shared_expert.down_proj", "model.layers.15.self_attn.q_proj", "model.layers.15.self_attn.k_proj", "model.layers.15.self_attn.v_proj", "model.layers.15.self_attn.o_proj", "model.layers.15.self_attn.g_proj", "model.layers.15.mlp.shared_expert.gate_proj", "model.layers.15.mlp.shared_expert.up_proj", "model.layers.15.mlp.shared_expert.down_proj", "model.layers.16.self_attn.q_proj", "model.layers.16.self_attn.k_proj", "model.layers.16.self_attn.v_proj", "model.layers.16.self_attn.o_proj", "model.layers.16.self_attn.g_proj", "model.layers.16.mlp.shared_expert.gate_proj", "model.layers.16.mlp.shared_expert.up_proj", "model.layers.16.mlp.shared_expert.down_proj", "model.layers.17.self_attn.q_proj", "model.layers.17.self_attn.k_proj", "model.layers.17.self_attn.v_proj", "model.layers.17.self_attn.o_proj", "model.layers.17.self_attn.g_proj", "model.layers.17.mlp.shared_expert.gate_proj", "model.layers.17.mlp.shared_expert.up_proj", "model.layers.17.mlp.shared_expert.down_proj", "model.layers.18.self_attn.q_proj", "model.layers.18.self_attn.k_proj", "model.layers.18.self_attn.v_proj", "model.layers.18.self_attn.o_proj", "model.layers.18.self_attn.g_proj", "model.layers.18.mlp.shared_expert.gate_proj", "model.layers.18.mlp.shared_expert.up_proj", "model.layers.18.mlp.shared_expert.down_proj", "model.layers.19.self_attn.q_proj", "model.layers.19.self_attn.k_proj", "model.layers.19.self_attn.v_proj", "model.layers.19.self_attn.o_proj", "model.layers.19.self_attn.g_proj", "model.layers.19.mlp.shared_expert.gate_proj", "model.layers.19.mlp.shared_expert.up_proj", "model.layers.19.mlp.shared_expert.down_proj", "model.layers.20.self_attn.q_proj", "model.layers.20.self_attn.k_proj", "model.layers.20.self_attn.v_proj", "model.layers.20.self_attn.o_proj", "model.layers.20.self_attn.g_proj", "model.layers.20.mlp.shared_expert.gate_proj", "model.layers.20.mlp.shared_expert.up_proj", "model.layers.20.mlp.shared_expert.down_proj", "model.layers.21.self_attn.q_proj", "model.layers.21.self_attn.k_proj", "model.layers.21.self_attn.v_proj", "model.layers.21.self_attn.o_proj", "model.layers.21.self_attn.g_proj", "model.layers.21.mlp.shared_expert.gate_proj", "model.layers.21.mlp.shared_expert.up_proj", "model.layers.21.mlp.shared_expert.down_proj", "model.layers.22.self_attn.q_proj", "model.layers.22.self_attn.k_proj", "model.layers.22.self_attn.v_proj", "model.layers.22.self_attn.o_proj", "model.layers.22.self_attn.g_proj", "model.layers.22.mlp.shared_expert.gate_proj", "model.layers.22.mlp.shared_expert.up_proj", "model.layers.22.mlp.shared_expert.down_proj", "model.layers.23.self_attn.q_proj", "model.layers.23.self_attn.k_proj", "model.layers.23.self_attn.v_proj", "model.layers.23.self_attn.o_proj", "model.layers.23.self_attn.g_proj", "model.layers.23.mlp.shared_expert.gate_proj", "model.layers.23.mlp.shared_expert.up_proj", "model.layers.23.mlp.shared_expert.down_proj", "model.layers.24.self_attn.q_proj", "model.layers.24.self_attn.k_proj", "model.layers.24.self_attn.v_proj", "model.layers.24.self_attn.o_proj", "model.layers.24.self_attn.g_proj", "model.layers.24.mlp.shared_expert.gate_proj", "model.layers.24.mlp.shared_expert.up_proj", "model.layers.24.mlp.shared_expert.down_proj", "model.layers.25.self_attn.q_proj", "model.layers.25.self_attn.k_proj", "model.layers.25.self_attn.v_proj", "model.layers.25.self_attn.o_proj", "model.layers.25.self_attn.g_proj", "model.layers.25.mlp.shared_expert.gate_proj", "model.layers.25.mlp.shared_expert.up_proj", "model.layers.25.mlp.shared_expert.down_proj", "model.layers.26.self_attn.q_proj", "model.layers.26.self_attn.k_proj", "model.layers.26.self_attn.v_proj", "model.layers.26.self_attn.o_proj", "model.layers.26.self_attn.g_proj", "model.layers.26.mlp.shared_expert.gate_proj", "model.layers.26.mlp.shared_expert.up_proj", "model.layers.26.mlp.shared_expert.down_proj", "model.layers.27.self_attn.q_proj", "model.layers.27.self_attn.k_proj", "model.layers.27.self_attn.v_proj", "model.layers.27.self_attn.o_proj", "model.layers.27.self_attn.g_proj", "model.layers.27.mlp.shared_expert.gate_proj", "model.layers.27.mlp.shared_expert.up_proj", "model.layers.27.mlp.shared_expert.down_proj", "model.layers.28.self_attn.q_proj", "model.layers.28.self_attn.k_proj", "model.layers.28.self_attn.v_proj", "model.layers.28.self_attn.o_proj", "model.layers.28.self_attn.g_proj", "model.layers.28.mlp.shared_expert.gate_proj", "model.layers.28.mlp.shared_expert.up_proj", "model.layers.28.mlp.shared_expert.down_proj", "model.layers.29.self_attn.q_proj", "model.layers.29.self_attn.k_proj", "model.layers.29.self_attn.v_proj", "model.layers.29.self_attn.o_proj", "model.layers.29.self_attn.g_proj", "model.layers.29.mlp.shared_expert.gate_proj", "model.layers.29.mlp.shared_expert.up_proj", "model.layers.29.mlp.shared_expert.down_proj", "model.layers.30.self_attn.q_proj", "model.layers.30.self_attn.k_proj", "model.layers.30.self_attn.v_proj", "model.layers.30.self_attn.o_proj", "model.layers.30.self_attn.g_proj", "model.layers.30.mlp.shared_expert.gate_proj", "model.layers.30.mlp.shared_expert.up_proj", "model.layers.30.mlp.shared_expert.down_proj", "model.layers.31.self_attn.q_proj", "model.layers.31.self_attn.k_proj", "model.layers.31.self_attn.v_proj", "model.layers.31.self_attn.o_proj", "model.layers.31.self_attn.g_proj", "model.layers.31.mlp.shared_expert.gate_proj", "model.layers.31.mlp.shared_expert.up_proj", "model.layers.31.mlp.shared_expert.down_proj", "model.layers.32.self_attn.q_proj", "model.layers.32.self_attn.k_proj", "model.layers.32.self_attn.v_proj", "model.layers.32.self_attn.o_proj", "model.layers.32.self_attn.g_proj", "model.layers.32.mlp.shared_expert.gate_proj", "model.layers.32.mlp.shared_expert.up_proj", "model.layers.32.mlp.shared_expert.down_proj", "model.layers.33.self_attn.q_proj", "model.layers.33.self_attn.k_proj", "model.layers.33.self_attn.v_proj", "model.layers.33.self_attn.o_proj", "model.layers.33.self_attn.g_proj", "model.layers.33.mlp.shared_expert.gate_proj", "model.layers.33.mlp.shared_expert.up_proj", "model.layers.33.mlp.shared_expert.down_proj", "model.layers.34.self_attn.q_proj", "model.layers.34.self_attn.k_proj", "model.layers.34.self_attn.v_proj", "model.layers.34.self_attn.o_proj", "model.layers.34.self_attn.g_proj", "model.layers.34.mlp.shared_expert.gate_proj", "model.layers.34.mlp.shared_expert.up_proj", "model.layers.34.mlp.shared_expert.down_proj", "model.layers.35.self_attn.q_proj", "model.layers.35.self_attn.k_proj", "model.layers.35.self_attn.v_proj", "model.layers.35.self_attn.o_proj", "model.layers.35.self_attn.g_proj", "model.layers.35.mlp.shared_expert.gate_proj", "model.layers.35.mlp.shared_expert.up_proj", "model.layers.35.mlp.shared_expert.down_proj", "model.layers.36.self_attn.q_proj", "model.layers.36.self_attn.k_proj", "model.layers.36.self_attn.v_proj", "model.layers.36.self_attn.o_proj", "model.layers.36.self_attn.g_proj", "model.layers.36.mlp.shared_expert.gate_proj", "model.layers.36.mlp.shared_expert.up_proj", "model.layers.36.mlp.shared_expert.down_proj", "model.layers.37.self_attn.q_proj", "model.layers.37.self_attn.k_proj", "model.layers.37.self_attn.v_proj", "model.layers.37.self_attn.o_proj", "model.layers.37.self_attn.g_proj", "model.layers.37.mlp.shared_expert.gate_proj", "model.layers.37.mlp.shared_expert.up_proj", "model.layers.37.mlp.shared_expert.down_proj", "model.layers.38.self_attn.q_proj", "model.layers.38.self_attn.k_proj", "model.layers.38.self_attn.v_proj", "model.layers.38.self_attn.o_proj", "model.layers.38.self_attn.g_proj", "model.layers.38.mlp.shared_expert.gate_proj", "model.layers.38.mlp.shared_expert.up_proj", "model.layers.38.mlp.shared_expert.down_proj", "model.layers.39.self_attn.q_proj", "model.layers.39.self_attn.k_proj", "model.layers.39.self_attn.v_proj", "model.layers.39.self_attn.o_proj", "model.layers.39.self_attn.g_proj", "model.layers.39.mlp.shared_expert.gate_proj", "model.layers.39.mlp.shared_expert.up_proj", "model.layers.39.mlp.shared_expert.down_proj", "model.layers.40.self_attn.q_proj", "model.layers.40.self_attn.k_proj", "model.layers.40.self_attn.v_proj", "model.layers.40.self_attn.o_proj", "model.layers.40.self_attn.g_proj", "model.layers.40.mlp.shared_expert.gate_proj", "model.layers.40.mlp.shared_expert.up_proj", "model.layers.40.mlp.shared_expert.down_proj", "model.layers.41.self_attn.q_proj", "model.layers.41.self_attn.k_proj", "model.layers.41.self_attn.v_proj", "model.layers.41.self_attn.o_proj", "model.layers.41.self_attn.g_proj", "model.layers.41.mlp.shared_expert.gate_proj", "model.layers.41.mlp.shared_expert.up_proj", "model.layers.41.mlp.shared_expert.down_proj", "model.layers.42.self_attn.q_proj", "model.layers.42.self_attn.k_proj", "model.layers.42.self_attn.v_proj", "model.layers.42.self_attn.o_proj", "model.layers.42.self_attn.g_proj", "model.layers.42.mlp.shared_expert.gate_proj", "model.layers.42.mlp.shared_expert.up_proj", "model.layers.42.mlp.shared_expert.down_proj", "model.layers.43.self_attn.q_proj", "model.layers.43.self_attn.k_proj", "model.layers.43.self_attn.v_proj", "model.layers.43.self_attn.o_proj", "model.layers.43.self_attn.g_proj", "model.layers.43.mlp.shared_expert.gate_proj", "model.layers.43.mlp.shared_expert.up_proj", "model.layers.43.mlp.shared_expert.down_proj", "model.layers.44.self_attn.q_proj", "model.layers.44.self_attn.k_proj", "model.layers.44.self_attn.v_proj", "model.layers.44.self_attn.o_proj", "model.layers.44.self_attn.g_proj", "model.layers.44.mlp.shared_expert.gate_proj", "model.layers.44.mlp.shared_expert.up_proj", "model.layers.44.mlp.shared_expert.down_proj", "model.layers.45.self_attn.q_proj", "model.layers.45.self_attn.k_proj", "model.layers.45.self_attn.v_proj", "model.layers.45.self_attn.o_proj", "model.layers.45.self_attn.g_proj", "model.layers.45.mlp.shared_expert.gate_proj", "model.layers.45.mlp.shared_expert.up_proj", "model.layers.45.mlp.shared_expert.down_proj", "model.layers.46.self_attn.q_proj", "model.layers.46.self_attn.k_proj", "model.layers.46.self_attn.v_proj", "model.layers.46.self_attn.o_proj", "model.layers.46.self_attn.g_proj", "model.layers.46.mlp.shared_expert.gate_proj", "model.layers.46.mlp.shared_expert.up_proj", "model.layers.46.mlp.shared_expert.down_proj", "model.layers.47.self_attn.q_proj", "model.layers.47.self_attn.k_proj", "model.layers.47.self_attn.v_proj", "model.layers.47.self_attn.o_proj", "model.layers.47.self_attn.g_proj", "model.layers.47.mlp.shared_expert.gate_proj", "model.layers.47.mlp.shared_expert.up_proj", "model.layers.47.mlp.shared_expert.down_proj", "lm_head" ], "kv_cache_scheme": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": null, "num_bits": 8, "observer": "minmax", "observer_kwargs": {}, "scale_dtype": null, "strategy": "tensor", "symmetric": true, "type": "float", "zp_dtype": null }, "quant_method": "compressed-tensors", "quantization_status": "compressed", "sparsity_config": {}, "transform_config": {}, "version": "0.17.0" }, "rms_norm_eps": 1e-06, "rope_parameters": { "full_attention": { "attention_factor": 1.4852030263919618, "beta_fast": 32.0, "beta_slow": 1.0, "factor": 128.0, "original_max_position_embeddings": 8192, "partial_rotary_factor": 0.5, "rope_theta": 500000.0, "rope_type": "yarn" }, "rope_theta": 10000.0, "rope_type": "default", "sliding_attention": { "partial_rotary_factor": 1.0, "rope_theta": 10000.0, "rope_type": "default" } }, "router_aux_loss_coef": 0.0, "shared_expert_intermediate_size": 1024, "sliding_window": 512, "swa_attention_sink_enabled": false, "swa_rope_parameters": { "partial_rotary_factor": 1.0, "rope_theta": 10000.0, "rope_type": "default" }, "tie_word_embeddings": false, "transformers_version": "5.12.0", "use_cache": true, "vocab_size": 100352 }