{ "architectures": [ "Olmo3SinkForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 0, "dtype": "bfloat16", "eos_token_id": 1, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 27648, "layer_types": [ "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", "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" ], "max_position_embeddings": 262144, "model_type": "olmo3", "num_attention_heads": 40, "num_hidden_layers": 64, "num_key_value_heads": 8, "pad_token_id": 2, "reuse_packing_metadata": true, "rms_norm_eps": 1e-06, "sink_init_value": 0.0, "sliding_window": 4096, "tie_word_embeddings": false, "transformers_version": "5.9.0", "use_cache": true, "vocab_size": 129280, "torch_dtype": "bfloat16", "rope_theta": 500000, "rope_scaling": { "attention_factor": 1.3465735902799727, "beta_fast": 32.0, "beta_slow": 1.0, "factor": 32.0, "original_max_position_embeddings": 8192, "rope_type": "yarn" }, "is_hybrid_swa": true, "hybrid_layer_pattern": [ 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0 ] }