{ "architectures": [ "DeepseekV4ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 0, "compress_ratios": [ 0, 0, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 0 ], "compress_rope_theta": 160000.0, "eos_token_id": 1, "hc_eps": 1e-06, "hc_mult": 4, "hc_sinkhorn_iters": 20, "head_dim": 512, "hidden_act": "silu", "hidden_size": 4096, "index_head_dim": 128, "index_n_heads": 64, "index_topk": 512, "initializer_range": 0.02, "max_position_embeddings": 1048576, "model_type": "deepseek_v4", "moe_intermediate_size": 2048, "n_routed_experts": 256, "n_shared_experts": 1, "norm_topk_prob": true, "num_attention_heads": 64, "num_experts_per_tok": 6, "num_hash_layers": 3, "num_hidden_layers": 43, "num_key_value_heads": 1, "num_nextn_predict_layers": 1, "o_groups": 8, "o_lora_rank": 1024, "q_lora_rank": 1024, "qk_rope_head_dim": 64, "quantization": { "group_size": 32, "bits": 4, "mode": "mxfp4", "model.layers.0.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.0.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.0.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.1.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.1.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.1.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.2.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.2.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.2.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.3.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.3.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.3.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.4.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.4.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.4.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.5.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.5.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.5.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.6.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.6.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.6.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.7.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.7.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.7.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.8.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.8.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.8.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.9.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.9.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.9.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.10.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.10.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.10.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.11.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.11.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.11.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.12.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.12.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.12.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.13.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.13.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.13.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.14.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.14.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.14.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.15.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.15.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.15.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.16.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.16.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.16.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.17.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.17.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.17.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.18.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.18.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.18.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.19.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.19.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.19.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.20.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.20.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.20.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.21.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.21.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.21.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.22.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.22.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.22.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.23.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.23.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.23.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.24.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.24.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.24.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.25.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.25.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.25.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.26.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.26.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.26.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.27.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.27.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.27.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.28.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.28.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.28.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.29.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.29.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.29.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.30.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.30.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.30.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.31.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.31.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.31.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.32.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.32.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.32.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.33.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.33.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.33.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.34.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.34.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.34.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.35.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.35.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.35.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.36.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.36.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.36.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.37.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.37.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.37.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.38.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.38.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.38.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.39.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.39.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.39.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.40.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.40.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.40.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.41.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.41.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.41.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.42.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.42.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.42.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" } }, "quantization_config": { "group_size": 32, "bits": 4, "mode": "mxfp4", "model.layers.0.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.0.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.0.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.1.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.1.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.1.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.2.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.2.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.2.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.3.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.3.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.3.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.4.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.4.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.4.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.5.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.5.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.5.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.6.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.6.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.6.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.7.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.7.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.7.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.8.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.8.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.8.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.9.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.9.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.9.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.10.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.10.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.10.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.11.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.11.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.11.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.12.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.12.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.12.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.13.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.13.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.13.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.14.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.14.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.14.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.15.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.15.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.15.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.16.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.16.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.16.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.17.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.17.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.17.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.18.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.18.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.18.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.19.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.19.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.19.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.20.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.20.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.20.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.21.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.21.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.21.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.22.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.22.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.22.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.23.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.23.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.23.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.24.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.24.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.24.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.25.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.25.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.25.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.26.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.26.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.26.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.27.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.27.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.27.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.28.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.28.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.28.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.29.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.29.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.29.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.30.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.30.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.30.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.31.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.31.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.31.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.32.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.32.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.32.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.33.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.33.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.33.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.34.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.34.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.34.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.35.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.35.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.35.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.36.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.36.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.36.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.37.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.37.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.37.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.38.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.38.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.38.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.39.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.39.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.39.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.40.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.40.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.40.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.41.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.41.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.41.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.42.ffn.switch_mlp.gate_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.42.ffn.switch_mlp.up_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" }, "model.layers.42.ffn.switch_mlp.down_proj": { "group_size": 32, "bits": 4, "mode": "mxfp4" } }, "rms_norm_eps": 1e-06, "rope_scaling": { "beta_fast": 32, "beta_slow": 1, "factor": 16, "original_max_position_embeddings": 65536, "type": "yarn" }, "rope_theta": 10000.0, "routed_scaling_factor": 1.5, "scoring_func": "sqrtsoftplus", "sliding_window": 128, "swiglu_limit": 10.0, "tie_word_embeddings": false, "topk_method": "noaux_tc", "torch_dtype": "bfloat16", "transformers_version": "4.57.1", "use_cache": true, "vocab_size": 129280 }