{ "exclude_modules": [], "quant_algo": "MIXED_PRECISION", "quant_method": "modelopt", "quantized_layers": { "lm_head": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.0.mlp.down_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.0.mlp.gate_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.0.mlp.up_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.0.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.0.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.0.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.0.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.1.mlp.down_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.1.mlp.gate_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.1.mlp.up_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.1.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.1.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.1.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.1.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.10.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.10.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.10.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.10.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.10.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.10.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.10.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.10.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.11.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.11.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.11.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.11.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.11.self_attn.kv_a_proj_with_mqa": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.11.self_attn.o_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.11.self_attn.q_a_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.11.self_attn.q_b_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.12.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.12.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.12.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.12.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.12.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.12.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.12.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.12.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.13.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.13.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.13.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.13.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.13.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.13.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.13.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.13.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.14.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.14.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.14.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.14.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.14.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.14.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.14.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.14.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.15.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.15.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.15.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.15.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.15.self_attn.kv_a_proj_with_mqa": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.15.self_attn.o_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.15.self_attn.q_a_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.15.self_attn.q_b_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.16.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.16.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.16.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.16.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.16.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.16.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.16.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.16.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.17.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.17.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.17.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.17.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.17.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.17.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.17.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.17.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.18.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.18.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.18.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.18.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.18.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.18.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.18.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.18.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.19.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.19.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.19.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.19.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.19.self_attn.kv_a_proj_with_mqa": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.19.self_attn.o_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.19.self_attn.q_a_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.19.self_attn.q_b_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.2.mlp.down_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.2.mlp.gate_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.2.mlp.up_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.2.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.2.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.2.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.2.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.20.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.20.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.20.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.20.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.20.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.20.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.20.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.20.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.21.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.21.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.21.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.21.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.21.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.21.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.21.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.21.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.22.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.22.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.22.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.22.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.22.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.22.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.22.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.22.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.23.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.23.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.23.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.23.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.23.self_attn.kv_a_proj_with_mqa": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.23.self_attn.o_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.23.self_attn.q_a_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.23.self_attn.q_b_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.24.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.24.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.24.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.24.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.24.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.24.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.24.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.24.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.25.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.25.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.25.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.25.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.25.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.25.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.25.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.25.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.26.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.26.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.26.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.26.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.26.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.26.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.26.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.26.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.27.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.27.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.27.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.27.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.27.self_attn.kv_a_proj_with_mqa": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.27.self_attn.o_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.27.self_attn.q_a_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.27.self_attn.q_b_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.28.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.28.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.28.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.28.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.28.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.28.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.28.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.28.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.29.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.29.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.29.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.29.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.29.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.29.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.29.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.29.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.3.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.3.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.3.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.3.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.3.self_attn.kv_a_proj_with_mqa": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.3.self_attn.o_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.3.self_attn.q_a_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.3.self_attn.q_b_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.30.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.30.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.30.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.30.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.30.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.30.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.30.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.30.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.31.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.31.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.31.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.31.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.31.self_attn.kv_a_proj_with_mqa": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.31.self_attn.o_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.31.self_attn.q_a_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.31.self_attn.q_b_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.32.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.32.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.32.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.32.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.32.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.32.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.32.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.32.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.33.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.33.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.33.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.33.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.33.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.33.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.33.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.33.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.34.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.34.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.34.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.34.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.34.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.34.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.34.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.34.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.35.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.35.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.35.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.35.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.35.self_attn.kv_a_proj_with_mqa": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.35.self_attn.o_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.35.self_attn.q_a_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.35.self_attn.q_b_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.36.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.36.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.36.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.36.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.36.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.36.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.36.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.36.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.37.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.37.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.37.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.37.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.37.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.37.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.37.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.37.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.38.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.38.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.38.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.38.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.38.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.38.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.38.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.38.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.39.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.39.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.39.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.39.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.39.self_attn.kv_a_proj_with_mqa": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.39.self_attn.o_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.39.self_attn.q_a_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.39.self_attn.q_b_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.4.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.4.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.4.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.4.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.4.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.4.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.4.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.4.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.40.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.40.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.40.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.40.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.40.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.40.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.40.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.40.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.41.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.41.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.41.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.41.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.41.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.41.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.41.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.41.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.42.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.42.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.42.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.42.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.42.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.42.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.42.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.42.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.43.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.43.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.43.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.43.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.43.self_attn.kv_a_proj_with_mqa": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.43.self_attn.o_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.43.self_attn.q_a_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.43.self_attn.q_b_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.44.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.44.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.44.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.44.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.44.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.44.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.44.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.44.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.45.mlp.experts": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.language_model.layers.45.mlp.shared_experts.down_proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.language_model.layers.45.mlp.shared_experts.gate_proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.language_model.layers.45.mlp.shared_experts.up_proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.language_model.layers.45.self_attn.indexer.weights_proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.language_model.layers.45.self_attn.indexer.wk": { "group_size": 32, "quant_algo": "MXFP8" }, "model.language_model.layers.45.self_attn.indexer.wq_b": { "group_size": 32, "quant_algo": "MXFP8" }, "model.language_model.layers.45.self_attn.kv_a_proj_with_mqa": { "group_size": 32, "quant_algo": "MXFP8" }, "model.language_model.layers.45.self_attn.kv_b_proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.language_model.layers.45.self_attn.o_proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.language_model.layers.45.self_attn.q_a_proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.language_model.layers.45.self_attn.q_b_proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.language_model.layers.5.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.5.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.5.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.5.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.5.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.5.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.5.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.5.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.6.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.6.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.6.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.6.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.6.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.6.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.6.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.6.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.7.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.7.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.7.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.7.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.7.self_attn.kv_a_proj_with_mqa": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.7.self_attn.o_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.7.self_attn.q_a_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.7.self_attn.q_b_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.8.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.8.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.8.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.8.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.8.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.8.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.8.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.8.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.9.mlp.experts": { "group_size": 16, "quant_algo": "NVFP4", "weight_scale_encoding": "csf_32x2_v1" }, "model.language_model.layers.9.mlp.shared_experts.down_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.9.mlp.shared_experts.gate_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.9.mlp.shared_experts.up_proj": { "quant_algo": "FP8_PB_WO", "weight_block_size": [ 128, 128 ] }, "model.language_model.layers.9.self_attn.k_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.9.self_attn.o_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.9.self_attn.q_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.language_model.layers.9.self_attn.v_proj": { "quant_algo": "MXFP8", "weight_block_size": [ 1, 32 ] }, "model.visual.blocks.0.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.0.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.0.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.0.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.0.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.1.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.1.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.1.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.1.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.1.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.10.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.10.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.10.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.10.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.10.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.11.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.11.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.11.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.11.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.11.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.12.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.12.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.12.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.12.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.12.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.13.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.13.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.13.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.13.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.13.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.14.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.14.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.14.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.14.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.14.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.15.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.15.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.15.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.15.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.15.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.16.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.16.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.16.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.16.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.16.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.17.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.17.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.17.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.17.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.17.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.18.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.18.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.18.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.18.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.18.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.19.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.19.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.19.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.19.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.19.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.2.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.2.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.2.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.2.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.2.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.20.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.20.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.20.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.20.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.20.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.21.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.21.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.21.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.21.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.21.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.22.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.22.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.22.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.22.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.22.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.23.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.23.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.23.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.23.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.23.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.3.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.3.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.3.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.3.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.3.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.4.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.4.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.4.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.4.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.4.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.5.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.5.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.5.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.5.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.5.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.6.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.6.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.6.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.6.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.6.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.7.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.7.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.7.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.7.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.7.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.8.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.8.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.8.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.8.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.8.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.9.attn.proj": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.9.attn.qkv": { "group_size": 32, "quant_algo": "MXFP8" }, "model.visual.blocks.9.mlp.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.9.mlp.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.blocks.9.mlp.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.merger.down_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.merger.gate_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.merger.proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" }, "model.visual.merger.up_proj": { "group_size": 16, "quant_algo": "W4A16_NVFP4" } } }