{ "architectures": [ "Dots1ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "eos_token_id": 151645, "first_k_dense_replace": 1, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 10944, "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", "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": 32768, "max_window_layers": 62, "model_type": "dots1", "moe_intermediate_size": 1408, "moe_layer_freq": 1, "n_group": 1, "n_routed_experts": 128, "n_shared_experts": 2, "norm_topk_prob": true, "num_attention_heads": 32, "num_experts_per_tok": 6, "num_hidden_layers": 62, "num_key_value_heads": 32, "pretraining_tp": 1, "quantization_config": { "config_groups": { "group_0": { "input_activations": null, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": 128, "num_bits": 4, "observer": "minmax", "observer_kwargs": {}, "strategy": "group", "symmetric": true, "type": "int" } } }, "format": "pack-quantized", "global_compression_ratio": null, "ignore": [ "model.layers.0.mlp.gate_proj", "model.layers.0.mlp.down_proj", "model.layers.1.mlp.shared_experts.gate_proj", "model.layers.1.mlp.shared_experts.up_proj", "model.layers.1.mlp.shared_experts.down_proj", "model.layers.2.mlp.shared_experts.gate_proj", "model.layers.2.mlp.shared_experts.up_proj", "model.layers.2.mlp.shared_experts.down_proj", "model.layers.3.mlp.shared_experts.gate_proj", "model.layers.3.mlp.shared_experts.up_proj", "model.layers.3.mlp.shared_experts.down_proj", "model.layers.4.mlp.shared_experts.gate_proj", "model.layers.4.mlp.shared_experts.up_proj", "model.layers.4.mlp.shared_experts.down_proj", "model.layers.5.mlp.shared_experts.gate_proj", "model.layers.5.mlp.shared_experts.up_proj", "model.layers.5.mlp.shared_experts.down_proj", "model.layers.6.mlp.shared_experts.gate_proj", "model.layers.6.mlp.shared_experts.up_proj", "model.layers.6.mlp.shared_experts.down_proj", "model.layers.7.mlp.shared_experts.gate_proj", "model.layers.7.mlp.shared_experts.up_proj", "model.layers.7.mlp.shared_experts.down_proj", "model.layers.8.mlp.shared_experts.gate_proj", "model.layers.8.mlp.shared_experts.up_proj", "model.layers.8.mlp.shared_experts.down_proj", "model.layers.9.mlp.shared_experts.gate_proj", "model.layers.9.mlp.shared_experts.up_proj", "model.layers.9.mlp.shared_experts.down_proj", "model.layers.10.mlp.shared_experts.gate_proj", "model.layers.10.mlp.shared_experts.up_proj", "model.layers.10.mlp.shared_experts.down_proj", "model.layers.11.mlp.shared_experts.gate_proj", "model.layers.11.mlp.shared_experts.up_proj", "model.layers.11.mlp.shared_experts.down_proj", "model.layers.12.mlp.shared_experts.gate_proj", "model.layers.12.mlp.shared_experts.up_proj", "model.layers.12.mlp.shared_experts.down_proj", "model.layers.13.mlp.shared_experts.gate_proj", "model.layers.13.mlp.shared_experts.up_proj", "model.layers.13.mlp.shared_experts.down_proj", "model.layers.14.mlp.shared_experts.gate_proj", "model.layers.14.mlp.shared_experts.up_proj", "model.layers.14.mlp.shared_experts.down_proj", "model.layers.15.mlp.shared_experts.gate_proj", "model.layers.15.mlp.shared_experts.up_proj", "model.layers.15.mlp.shared_experts.down_proj", "model.layers.16.mlp.shared_experts.gate_proj", "model.layers.16.mlp.shared_experts.up_proj", "model.layers.16.mlp.shared_experts.down_proj", "model.layers.17.mlp.shared_experts.gate_proj", "model.layers.17.mlp.shared_experts.up_proj", "model.layers.17.mlp.shared_experts.down_proj", "model.layers.18.mlp.shared_experts.gate_proj", "model.layers.18.mlp.shared_experts.up_proj", "model.layers.18.mlp.shared_experts.down_proj", "model.layers.19.mlp.shared_experts.gate_proj", "model.layers.19.mlp.shared_experts.up_proj", "model.layers.19.mlp.shared_experts.down_proj", "model.layers.20.mlp.shared_experts.gate_proj", "model.layers.20.mlp.shared_experts.up_proj", "model.layers.20.mlp.shared_experts.down_proj", "model.layers.21.mlp.shared_experts.gate_proj", "model.layers.21.mlp.shared_experts.up_proj", "model.layers.21.mlp.shared_experts.down_proj", "model.layers.22.mlp.shared_experts.gate_proj", "model.layers.22.mlp.shared_experts.up_proj", "model.layers.22.mlp.shared_experts.down_proj", "model.layers.23.mlp.shared_experts.gate_proj", "model.layers.23.mlp.shared_experts.up_proj", "model.layers.23.mlp.shared_experts.down_proj", "model.layers.24.mlp.shared_experts.gate_proj", "model.layers.24.mlp.shared_experts.up_proj", "model.layers.24.mlp.shared_experts.down_proj", "model.layers.25.mlp.shared_experts.gate_proj", "model.layers.25.mlp.shared_experts.up_proj", "model.layers.25.mlp.shared_experts.down_proj", "model.layers.26.mlp.shared_experts.gate_proj", "model.layers.26.mlp.shared_experts.up_proj", "model.layers.26.mlp.shared_experts.down_proj", "model.layers.27.mlp.shared_experts.gate_proj", "model.layers.27.mlp.shared_experts.up_proj", "model.layers.27.mlp.shared_experts.down_proj", "model.layers.28.mlp.shared_experts.gate_proj", "model.layers.28.mlp.shared_experts.up_proj", "model.layers.28.mlp.shared_experts.down_proj", "model.layers.29.mlp.shared_experts.gate_proj", "model.layers.29.mlp.shared_experts.up_proj", "model.layers.29.mlp.shared_experts.down_proj", "model.layers.30.mlp.shared_experts.gate_proj", "model.layers.30.mlp.shared_experts.up_proj", "model.layers.30.mlp.shared_experts.down_proj", "model.layers.31.mlp.shared_experts.gate_proj", "model.layers.31.mlp.shared_experts.up_proj", "model.layers.31.mlp.shared_experts.down_proj", "model.layers.32.mlp.shared_experts.gate_proj", "model.layers.32.mlp.shared_experts.up_proj", "model.layers.32.mlp.shared_experts.down_proj", "model.layers.33.mlp.shared_experts.gate_proj", "model.layers.33.mlp.shared_experts.up_proj", "model.layers.33.mlp.shared_experts.down_proj", "model.layers.34.mlp.shared_experts.gate_proj", "model.layers.34.mlp.shared_experts.up_proj", "model.layers.34.mlp.shared_experts.down_proj", "model.layers.35.mlp.shared_experts.gate_proj", "model.layers.35.mlp.shared_experts.up_proj", "model.layers.35.mlp.shared_experts.down_proj", "model.layers.36.mlp.shared_experts.gate_proj", "model.layers.36.mlp.shared_experts.up_proj", "model.layers.36.mlp.shared_experts.down_proj", "model.layers.37.mlp.shared_experts.gate_proj", "model.layers.37.mlp.shared_experts.up_proj", "model.layers.37.mlp.shared_experts.down_proj", "model.layers.38.mlp.shared_experts.gate_proj", "model.layers.38.mlp.shared_experts.up_proj", "model.layers.38.mlp.shared_experts.down_proj", "model.layers.39.mlp.shared_experts.gate_proj", "model.layers.39.mlp.shared_experts.up_proj", "model.layers.39.mlp.shared_experts.down_proj", "model.layers.40.mlp.shared_experts.gate_proj", "model.layers.40.mlp.shared_experts.up_proj", "model.layers.40.mlp.shared_experts.down_proj", "model.layers.41.mlp.shared_experts.gate_proj", "model.layers.41.mlp.shared_experts.up_proj", "model.layers.41.mlp.shared_experts.down_proj", "model.layers.42.mlp.shared_experts.gate_proj", "model.layers.42.mlp.shared_experts.up_proj", "model.layers.42.mlp.shared_experts.down_proj", "model.layers.43.mlp.shared_experts.gate_proj", "model.layers.43.mlp.shared_experts.up_proj", "model.layers.43.mlp.shared_experts.down_proj", "model.layers.44.mlp.shared_experts.gate_proj", "model.layers.44.mlp.shared_experts.up_proj", "model.layers.44.mlp.shared_experts.down_proj", "model.layers.45.mlp.shared_experts.gate_proj", "model.layers.45.mlp.shared_experts.up_proj", "model.layers.45.mlp.shared_experts.down_proj", "model.layers.46.mlp.shared_experts.gate_proj", "model.layers.46.mlp.shared_experts.up_proj", "model.layers.46.mlp.shared_experts.down_proj", "model.layers.47.mlp.shared_experts.gate_proj", "model.layers.47.mlp.shared_experts.up_proj", "model.layers.47.mlp.shared_experts.down_proj", "model.layers.48.mlp.shared_experts.gate_proj", "model.layers.48.mlp.shared_experts.up_proj", "model.layers.48.mlp.shared_experts.down_proj", "model.layers.49.mlp.shared_experts.gate_proj", "model.layers.49.mlp.shared_experts.up_proj", "model.layers.49.mlp.shared_experts.down_proj", "model.layers.50.mlp.shared_experts.gate_proj", "model.layers.50.mlp.shared_experts.up_proj", "model.layers.50.mlp.shared_experts.down_proj", "model.layers.51.mlp.shared_experts.gate_proj", "model.layers.51.mlp.shared_experts.up_proj", "model.layers.51.mlp.shared_experts.down_proj", "model.layers.52.mlp.shared_experts.gate_proj", "model.layers.52.mlp.shared_experts.up_proj", "model.layers.52.mlp.shared_experts.down_proj", "model.layers.53.mlp.shared_experts.gate_proj", "model.layers.53.mlp.shared_experts.up_proj", "model.layers.53.mlp.shared_experts.down_proj", "model.layers.54.mlp.shared_experts.gate_proj", "model.layers.54.mlp.shared_experts.up_proj", "model.layers.54.mlp.shared_experts.down_proj", "model.layers.55.mlp.shared_experts.gate_proj", "model.layers.55.mlp.shared_experts.up_proj", "model.layers.55.mlp.shared_experts.down_proj", "model.layers.56.mlp.shared_experts.gate_proj", "model.layers.56.mlp.shared_experts.up_proj", "model.layers.56.mlp.shared_experts.down_proj", "model.layers.57.mlp.shared_experts.gate_proj", "model.layers.57.mlp.shared_experts.up_proj", "model.layers.57.mlp.shared_experts.down_proj", "model.layers.58.mlp.shared_experts.gate_proj", "model.layers.58.mlp.shared_experts.up_proj", "model.layers.58.mlp.shared_experts.down_proj", "model.layers.59.mlp.shared_experts.gate_proj", "model.layers.59.mlp.shared_experts.up_proj", "model.layers.59.mlp.shared_experts.down_proj", "model.layers.60.mlp.shared_experts.gate_proj", "model.layers.60.mlp.shared_experts.up_proj", "model.layers.60.mlp.shared_experts.down_proj", "model.layers.61.mlp.shared_experts.gate_proj", "model.layers.61.mlp.shared_experts.up_proj", "model.layers.61.mlp.shared_experts.down_proj", "lm_head" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed" }, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000000, "routed_scaling_factor": 2.5, "scoring_func": "noaux_tc", "sliding_window": null, "tie_word_embeddings": false, "topk_group": 1, "torch_dtype": "bfloat16", "transformers_version": "4.53.0.dev0", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064 }