{ "_name_or_path": "/mnt/models/Laguna-XS.2/", "add_cross_attention": false, "architectures": [ "LagunaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "attribute_map": {}, "auto_map": { "AutoConfig": "configuration_laguna.LagunaConfig", "AutoModelForCausalLM": "modeling_laguna.LagunaForCausalLM" }, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 2, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": [ 2, 24 ], "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "fused_spec_config": null, "gating": true, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "intermediate_size": 8192, "is_decoder": false, "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" ], "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 131072, "metadata": null, "min_length": 0, "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": "", "moe_apply_router_weight_on_input": false, "moe_cte_ep_degree": 1, "moe_cte_tp_degree": 4, "moe_intermediate_size": 512, "moe_routed_scaling_factor": 2.5, "moe_tkg_ep_degree": 1, "moe_tkg_tp_degree": 4, "n_shared_experts": 1, "neuron_config": { "activation_quantization_type": null, "allow_input_truncation": false, "apply_seq_ids_mask": false, "async_mode": false, "attention_dp_degree": 1, "attention_dtype": null, "attn_block_cte_nki_kernel_enabled": false, "attn_block_tkg_nki_kernel_cache_update": false, "attn_block_tkg_nki_kernel_cascaded_attention": false, "attn_block_tkg_nki_kernel_disable_gpsimd_sb2sb": false, "attn_block_tkg_nki_kernel_enabled": false, "attn_block_tkg_nki_kernel_use_online_softmax": true, "attn_cls": "NeuronLlamaAttention", "attn_kernel_enabled": true, "attn_tkg_builtin_kernel_enabled": false, "attn_tkg_nki_kernel_enabled": false, "batch_size": 4, "blockwise_matmul_config": { "always_augment_inputs_for_blockwise_matmul": false, "block_sharding_strategy": { "__objclass__": { "__module__": "nkilib.core.moe.moe_cte.moe_cte_utils", "__name__": "BlockShardStrategy" }, "_name_": "HI_LO", "_sort_order_": 0, "_value_": 0 }, "block_size": 512, "blockwise_nki_autograd_cls": null, "logical_nc_config": { "__objclass__": { "__module__": "neuronx_distributed.utils.model_utils", "__name__": "LogicalNCConfig" }, "_name_": "LNC_2", "_sort_order_": 1, "_value_": 2 }, "num_static_blocks": null, "optimized_block_to_token_mapping": true, "pad_num_blocks_to_even": false, "parallelize_token_to_block_mapping": true, "skip_dma_token": false, "skip_dma_weight": false, "use_block_parallel": false, "use_shard_on_block_dynamic_while": false, "use_shard_on_intermediate_dynamic_while": false, "use_torch_block_wise": true }, "bucket_n_active_tokens": false, "buckets": [ 4096 ], "capacity_factor": null, "cast_type": "config", "cc_pipeline_tiling_factor": 2, "chunked_prefill_config": null, "context_encoding_buckets": null, "cp_degree": 1, "ctx_batch_size": 1, "disable_argmax_kernel": false, "disable_kv_cache_tiling": false, "disable_numeric_cc_token": false, "dma_order_config": null, "draft_model_modules_to_not_convert": null, "eagle_rolling_buffer_kernel_enabled": false, "early_expert_affinity_modulation": false, "enable_bucketing": true, "enable_cte_modular_flow": false, "enable_eagle_draft_input_norm": false, "enable_eagle_speculation": false, "enable_fused_speculation": false, "enable_long_context_mode": false, "enable_output_completion_notifications": false, "enable_spill_reload_dge": false, "enable_token_tree": false, "enable_ve_data_parallel": false, "ep_degree": 1, "ep_dispatch_cc_option": "AR_AG", "expert_mlp_nki_kernel_enabled": null, "flash_decoding_enabled": false, "fused_qkv": false, "fused_rmsnorm_skip_gamma": false, "fused_shared_experts": false, "gate_clamp_lower_limit": null, "gate_clamp_upper_limit": null, "glu_mlp": true, "glu_type": "glu", "hidden_act_bias": 0.0, "hidden_act_scaling_factor": 1.0, "hybrid_sharding_config": null, "is_block_kv_layout": false, "is_chunked_prefill": false, "is_continuous_batching": true, "is_eagle3": false, "is_eagle_draft": false, "is_full_model_shuffled": false, "is_hidden_dim_shuffled": false, "is_intermediate_dim_shuffled": false, "is_medusa": false, "is_mxfp4_compute": false, "is_prefill_stage": null, "is_prefix_caching": false, "k_cache_transposed": false, "kv_cache_batch_size": 4, "kv_cache_padding_size": 0, "kv_cache_quant": false, "kv_cache_tiling": false, "kv_cache_update_with_kernel": false, "kv_quant_config": null, "layer_boundary_markers": false, "lm_head_pad": true, "lm_head_pad_alignment_size": 1, "local_ranks_size": 4, "logical_nc_config": 2, "lora_config": null, "max_batch_size": 4, "max_context_length": 4096, "max_length": 4096, "max_new_tokens": null, "medusa_speculation_length": 0, "medusa_tree": null, "mlp_cp_degree": 1, "mlp_kernel_enabled": false, "mlp_kernel_fuse_residual_add": false, "mlp_tkg_nki_kernel_enabled": false, "modules_to_not_convert": null, "moe_ep_degree": 1, "moe_fused_nki_kernel_enabled": true, "moe_mask_padded_tokens": false, "moe_tp_degree": 4, "n_active_tokens": 4096, "n_positions": 4096, "normalize_top_k_affinities": true, "num_medusa_heads": 0, "on_cpu": false, "on_device_sampling_config": { "deterministic": false, "do_sample": false, "dynamic": true, "global_topk": 256, "on_device_sampling_config": true, "sampling_dp_degree": 1, "temperature": 1.0, "top_k": 1, "top_k_kernel_enabled": true, "top_p": 1.0 }, "out_proj_kernel_enabled": false, "output_logits": false, "overrides_torch_dtype": true, "pa_block_size": 4096, "pa_num_blocks": 2, "padded_hidden_size": null, "padded_intermediate_size": null, "padding_side": "right", "pp_degree": 1, "pre_rope_rmsnorm": false, "prefix_buckets": null, "qk_layernorm": false, "qkv_cte_nki_kernel_fuse_rope": false, "qkv_kernel_enabled": false, "qkv_kernel_fuse_residual_add": false, "qkv_kernel_nbsd_layout": false, "qkv_nki_kernel_enabled": false, "quantization_block_axis": null, "quantization_block_size": null, "quantization_dtype": "int8", "quantization_scale_dtype": "f32", "quantization_type": "per_tensor_symmetric", "quantize_clamp_bound": Infinity, "quantized": false, "quantized_checkpoints_path": null, "quantized_mlp_kernel_enabled": false, "return_expert_index": false, "return_router_logits": false, "rmsnorm_quantize_kernel_enabled": false, "router_config": { "act_fn": "sigmoid", "dtype": "float32" }, "router_topk_nki_kernel_enabled": null, "rpl_reduce_dtype": null, "save_sharded_checkpoint": true, "scratchpad_page_size": null, "seq_len": 4096, "seq_len_threshold_for_cc_tiling": 16384, "sequence_parallel_enabled": false, "shared_experts_sequence_parallel_enabled": false, "shared_mlp_nki_kernel_enabled": null, "skip_sharding": false, "skip_warmup": false, "spec_batch_size": 4, "speculation_length": 0, "start_rank_id": 0, "strided_context_parallel_kernel_enabled": false, "switch_cc": false, "target": null, "tensor_capture_config": null, "tensor_replacement_config": null, "tile_cc": false, "tkg_batch_size": 4, "token_generation_batches": null, "token_generation_buckets": null, "token_tree_config": null, "torch_dtype": "bfloat16", "tp_degree": 4, "transpose_shared_experts_weights": false, "up_clamp_lower_limit": null, "up_clamp_upper_limit": null, "use_index_calc_kernel": false, "vocab_parallel": false, "weight_gather_seq_len_threshold": 32768, "weights_to_skip_layout_optimization": [], "windowed_context_encoding_size": null, "world_size": 4 }, "no_repeat_ngram_size": 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_beam_groups": 1, "num_beams": 1, "num_cores_per_group": 1, "num_experts": 256, "num_experts_per_tok": 8, "num_hidden_layers": 40, "num_key_value_heads": 8, "num_local_experts": 256, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 9, "partial_rotary_factor": 0.5, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-06, "rope_parameters": { "full_attention": { "attention_factor": 1.0, "beta_fast": 64.0, "beta_slow": 1.0, "factor": 32.0, "original_max_position_embeddings": 4096, "partial_rotary_factor": 0.5, "rope_theta": 500000.0, "rope_type": "yarn" }, "original_max_position_embeddings": 4096, "rope_type": "yarn", "sliding_attention": { "partial_rotary_factor": 1.0, "rope_theta": 10000.0, "rope_type": "default" } }, "router_aux_loss_coef": 0.0, "sep_token_id": null, "shared_expert_intermediate_size": 512, "sliding_window": 512, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torchscript": false, "transformers_version": "4.57.6", "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 100352 }