{ "architectures": [ "HybridEchoForCausalLM" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_hybrid.HybridEchoConfig", "AutoModel": "modeling_hybrid.HybridEchoModel", "AutoModelForCausalLM": "modeling_hybrid.HybridEchoForCausalLM" }, "bos_token_id": 151643, "dsrn_injection_stride": 3, "dsrn_state_dim": 1792, "dsrn_use_triton": false, "dtype": "bfloat16", "eos_token_id": 151645, "gate_bias_init": 1.0, "hidden_act": "silu", "hidden_size": 1536, "initializer_range": 0.02, "intermediate_size": 8960, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 32768, "max_window_layers": 21, "model_type": "echo_hybrid", "num_attention_heads": 12, "num_hidden_layers": 28, "num_key_value_heads": 2, "pad_token_id": null, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 1000000.0, "rope_type": "default" }, "sliding_window": null, "tie_word_embeddings": false, "transformers_version": "5.2.0", "use_cache": true, "use_kv_cache": true, "use_sliding_window": false, "vocab_size": 151936 }