{ "producer": { "name": "modelopt", "version": "0.44.0" }, "quantization": { "quant_algo": "MIXED_PRECISION", "kv_cache_quant_algo": "FP8", "quantized_layers": { "model.language_model.layers.0.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.1.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.2.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.3.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.4.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.5.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.6.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.7.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.8.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.9.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.10.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.11.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.12.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.13.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.14.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.15.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.16.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.17.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.18.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.19.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.30.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.31.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.32.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.33.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.34.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 }, "model.language_model.layers.35.mlp.experts": { "quant_algo": "W4A16_NVFP4", "group_size": 16 } }, "exclude_modules": [ "mtp.layers.0*", "mtp*" ] } }