{ "architectures": [ "MellumForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 0, "dtype": "bfloat16", "eos_token_id": 28, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2304, "initializer_range": 0.02, "intermediate_size": 7168, "layer_types": [ "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention" ], "max_position_embeddings": 131072, "max_window_layers": 0, "mlp_layer_types": [ "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse" ], "model_type": "mellum", "moe_intermediate_size": 896, "norm_topk_prob": true, "num_attention_heads": 32, "num_experts": 64, "num_experts_per_tok": 8, "num_hidden_layers": 28, "num_key_value_heads": 4, "output_router_logits": false, "quantization": { "group_size": 64, "bits": 6, "mode": "affine", "model.layers.0.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.1.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.2.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.3.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.4.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.5.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.6.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.7.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.8.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.9.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.10.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.11.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.12.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.13.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.14.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.15.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.16.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.17.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.18.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.19.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.20.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.21.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.22.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.23.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.24.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.25.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.26.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.27.mlp.gate": { "group_size": 64, "bits": 8 } }, "quantization_config": { "group_size": 64, "bits": 6, "mode": "affine", "model.layers.0.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.1.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.2.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.3.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.4.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.5.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.6.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.7.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.8.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.9.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.10.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.11.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.12.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.13.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.14.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.15.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.16.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.17.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.18.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.19.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.20.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.21.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.22.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.23.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.24.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.25.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.26.mlp.gate": { "group_size": 64, "bits": 8 }, "model.layers.27.mlp.gate": { "group_size": 64, "bits": 8 } }, "rms_norm_eps": 1e-06, "rope_parameters": { "full_attention": { "rope_type": "yarn", "rope_theta": 500000.0, "factor": 16.0, "original_max_position_embeddings": 8192, "beta_fast": 32.0, "beta_slow": 1.0, "attention_factor": 1.2772588722239782 }, "sliding_attention": { "rope_type": "default", "rope_theta": 500000.0 } }, "router_aux_loss_coef": 0.001, "sliding_window": 1024, "tie_word_embeddings": false, "transformers_version": "5.8.1", "use_cache": true, "use_sliding_window": true, "vocab_size": 98304 }