{ "architectures": [ "LiveMemForCausalLM" ], "auto_map": { "AutoConfig": "configuration_livemem.LiveMemConfig", "AutoModel": "modeling_livemem.LiveMemModel", "AutoModelForCausalLM": "modeling_livemem.LiveMemForCausalLM" }, "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "dtype": "bfloat16", "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 9728, "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", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 262144, "max_window_layers": 36, "mem_conv_bias": false, "mem_conv_size": 4, "mem_expand_v": 1.0, "mem_head_dim": 128, "mem_layers": null, "mem_norm_eps": 1e-06, "mem_num_heads": 32, "mem_num_v_heads": 32, "mem_o_proj_zero_init": true, "memory_design": "X", "model_type": "livemem", "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 8, "pad_token_id": 151643, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 5000000, "rope_type": "default" }, "sliding_window": null, "tie_word_embeddings": true, "transformers_version": "5.12.1", "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 }