| { |
| "producer": { |
| "name": "modelopt", |
| "version": "0.45.0" |
| }, |
| "quantization": { |
| "quant_algo": "NVFP4", |
| "kv_cache_quant_algo": null, |
| "quantized_layers": { |
| "model.language_model.layers.0.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.0.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.0.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.0.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.1.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.1.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.1.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.1.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.2.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.2.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.2.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.2.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.3.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.3.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.3.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.3.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.4.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.4.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.4.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.4.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.5.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.5.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.5.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.5.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.6.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.6.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.6.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.6.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.7.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.7.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.7.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.7.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.8.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.8.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.8.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.8.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.9.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.9.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.9.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.9.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.10.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.10.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.10.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.10.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.11.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.11.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.11.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.11.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.12.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.12.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.12.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.12.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.13.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.13.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.13.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.13.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.14.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.14.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.14.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.14.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.15.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.15.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.15.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.15.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.16.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.16.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.16.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.16.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.17.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.17.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.17.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.17.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.18.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.18.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.18.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.18.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.19.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.19.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.19.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.19.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.20.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.20.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.20.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.20.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.21.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.21.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.21.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.21.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.22.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.22.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.22.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.22.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.23.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.23.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.23.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.23.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.24.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.24.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.24.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.24.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.25.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.25.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.25.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.25.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.26.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.26.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.26.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.26.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.27.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.27.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.27.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.27.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.28.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.28.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.28.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.28.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.29.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.29.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.29.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.29.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.30.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.30.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.30.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.30.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.31.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.31.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.31.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.31.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.32.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.32.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.32.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.32.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.33.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.33.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.33.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.33.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.34.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.34.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.34.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.34.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.35.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.35.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.35.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.35.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.36.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.36.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.36.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.36.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.37.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.37.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.37.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.37.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.38.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.38.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.38.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.38.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.39.mlp.experts": { |
| "quant_algo": "W4A16_NVFP4", |
| "group_size": 16 |
| }, |
| "model.language_model.layers.39.mlp.shared_expert.gate_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.39.mlp.shared_expert.up_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| }, |
| "model.language_model.layers.39.mlp.shared_expert.down_proj": { |
| "quant_algo": "NVFP4_AWQ", |
| "group_size": 16, |
| "has_zero_point": false, |
| "pre_quant_scale": true |
| } |
| } |
| } |
| } |