{ "architectures": [ "BusyBeaverQDeltaForCausalLM" ], "conv_kernel_size": 4, "dtype": "float32", "hidden_size": 384, "initializer_range": 0.02, "intermediate_size": 1152, "layer_pattern": [ "delta", "delta", "delta", "attention" ], "max_position_embeddings": 2048, "model_type": "busybeaver_qdelta", "mtp_steps": 2, "num_attention_heads": 6, "num_hidden_layers": 16, "num_key_value_heads": 2, "num_tool_families": 8, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "transformers_version": "4.57.6", "use_mtp": true, "use_router_aux": true, "vocab_size": 16384 }