{ "producer": { "name": "modelopt", "version": "0.47.0rc1.dev129+g333ace1bc" }, "quantization": { "quant_algo": "MIXED_PRECISION", "kv_cache_quant_algo": null, "group_size": 16, "exclude_modules": [ "lm_head", "model.embed_tokens", "model.layers.*.mlp.down_proj", "model.layers.*.mlp.gate", "model.layers.*.mlp.gate_proj", "model.layers.*.mlp.shared_experts.down_proj", "model.layers.*.mlp.shared_experts.gate_proj", "model.layers.*.mlp.shared_experts.up_proj", "model.layers.*.mlp.up_proj", "model.layers.*.self_attn.kv_a_proj_with_mqa", "model.layers.*.self_attn.kv_b_proj", "model.layers.*.self_attn.o_proj", "model.layers.*.self_attn.q_a_proj", "model.layers.*.self_attn.q_b_proj" ], "quantized_layers": { "model.layers.1.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.10.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.11.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.12.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.13.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.14.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.15.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.16.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.17.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.18.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.19.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.2.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.20.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.21.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.22.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.23.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.24.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.25.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.26.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.27.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.28.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.29.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.3.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.30.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.31.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.32.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.33.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.34.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.35.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.36.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.37.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.38.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.39.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.4.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.40.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.41.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.42.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.43.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.44.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.45.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.46.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.5.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.6.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.7.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.8.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.9.mlp.experts": { "quant_algo": "NVFP4", "group_size": 16 } } } }