{ "architectures": [ "ZgcmForCausalLM" ], "model_type": "zgcm", "auto_map": { "AutoConfig": "configuration_zgcm.ZgcmConfig", "AutoModel": "modeling_zgcm.ZgcmModel", "AutoModelForCausalLM": "modeling_zgcm.ZgcmForCausalLM" }, "vocab_size": 155136, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "head_dim": 128, "hidden_act": "silu", "rms_norm_eps": 1e-06, "rope_theta": 10000000.0, "partial_rotary_factor": 0.334, "max_position_embeddings": 262144, "sliding_window": 128, "window_attn_skip_freq": 6, "layer_types": [ "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention" ], "attention_gate_layers": [ true, true, true, true, true, false, true, true, true, true, true, false, true, true, true, true, true, false, true, true, true, true, true, false, true, true, true, true, true, false, true, true ], "attention_bias": false, "tie_word_embeddings": false, "pad_token_id": 154820, "eos_token_id": 154820, "bos_token_id": null, "torch_dtype": "bfloat16", "transformers_version": "5.10.2", "use_cache": true }