{ "activation_sparsity_pattern": [ 0.95, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "altup_active_idx": 0, "altup_coef_clip": 120.0, "altup_correct_scale": true, "altup_num_inputs": 4, "architectures": [ "Gemma3nForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 2, "dtype": "float16", "eos_token_id": 1, "final_logit_softcapping": 30.0, "head_dim": 256, "hidden_activation": "gelu_pytorch_tanh", "hidden_size": 2048, "hidden_size_per_layer_input": 256, "initializer_range": 0.02, "intermediate_size": [ 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096, 4096 ], "laurel_rank": 64, "layer_types": [ "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention" ], "max_position_embeddings": 32768, "model_type": "gemma3n_text", "num_attention_heads": 8, "num_hidden_layers": 16, "num_key_value_heads": 2, "num_kv_shared_layers": 0, "pad_token_id": 0, "quantization_config": { "_load_in_4bit": true, "_load_in_8bit": false, "bnb_4bit_compute_dtype": "bfloat16", "bnb_4bit_quant_storage": "uint8", "bnb_4bit_quant_type": "nf4", "bnb_4bit_use_double_quant": true, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": null, "llm_int8_threshold": 6.0, "load_in_4bit": true, "load_in_8bit": false, "quant_method": "bitsandbytes" }, "rms_norm_eps": 1e-06, "rope_local_base_freq": 10000.0, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": 512, "transformers_version": "4.57.6", "use_cache": true, "vocab_size": 262400, "vocab_size_per_layer_input": 262144 }