{ "model_type": "maseek", "architectures": [ "Maseek" ], "vocab_size": 50257, "n_embd": 512, "n_layer": 6, "block_size": 1024, "dropout": 0.1, "ssm_d_state": 16, "moe_n_experts": 8, "moe_k_top": 2, "torch_dtype": "float32" }