{ "_name_or_path": "poolside/Laguna-XS.2", "architectures": [ "DuoLagunaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoModelForCausalLM": "modeling_duo_laguna.DuoLagunaForCausalLM" }, "bos_token_id": 2, "chunk_size_feed_forward": 0, "dtype": "bfloat16", "duo_attention": { "architecture": "laguna", "base_config_name_or_path": null, "base_model_name_or_path": "poolside/Laguna-XS.2", "enabled": true, "format_version": 1, "full_attention_heads_file": "duo_attention/full_attention_heads.pt", "full_attention_heads_tsv_file": "duo_attention/full_attention_heads.tsv", "patch_mode": "eval", "recent_size": 256, "sink_size": 64, "training_recent_size": 256, "training_sink_size": 64 }, "eos_token_id": [ 2, 24 ], "gating": true, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 8192, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "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" ], "max_position_embeddings": 262144, "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" ], "model_type": "laguna", "moe_apply_router_weight_on_input": false, "moe_intermediate_size": 512, "moe_routed_scaling_factor": 2.5, "moe_router_logit_softcapping": 0.0, "num_attention_heads": 48, "num_attention_heads_per_layer": [ 48, 64, 64, 64, 48, 64, 64, 64, 48, 64, 64, 64, 48, 64, 64, 64, 48, 64, 64, 64, 48, 64, 64, 64, 48, 64, 64, 64, 48, 64, 64, 64, 48, 64, 64, 64, 48, 64, 64, 64 ], "num_experts": 256, "num_experts_per_tok": 8, "num_hidden_layers": 40, "num_key_value_heads": 8, "output_attentions": false, "output_hidden_states": false, "output_router_logits": false, "pad_token_id": 9, "partial_rotary_factor": 0.5, "problem_type": null, "return_dict": true, "rms_norm_eps": 1e-06, "rope_parameters": { "full_attention": { "attention_factor": 1.0, "beta_fast": 64.0, "beta_slow": 1.0, "factor": 64.0, "original_max_position_embeddings": 4096, "partial_rotary_factor": 0.5, "rope_theta": 500000.0, "rope_type": "yarn" }, "original_max_position_embeddings": 4096, "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": 512, "sliding_window": 512, "tie_word_embeddings": false, "transformers_version": "5.9.0", "use_cache": true, "vocab_size": 100352 }