{ "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "dtype": "bfloat16", "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 65536, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": null, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 500000, "rope_type": "default" }, "tie_word_embeddings": false, "transformers_version": "5.5.4", "use_cache": true, "vocab_size": 196608, "quantization_config": { "config_groups": { "group_0": { "input_activations": { "dynamic": false, "num_bits": 8, "type": "float" }, "weights": { "dynamic": false, "num_bits": 8, "type": "float" }, "targets": [ "model.layers.10.self_attn.k_proj", "model.layers.10.self_attn.o_proj", "model.layers.10.self_attn.q_proj", "model.layers.10.self_attn.v_proj", "model.layers.11.self_attn.k_proj", "model.layers.11.self_attn.o_proj", "model.layers.11.self_attn.q_proj", "model.layers.11.self_attn.v_proj", "model.layers.12.self_attn.k_proj", "model.layers.12.self_attn.o_proj", "model.layers.12.self_attn.q_proj", "model.layers.12.self_attn.v_proj", "model.layers.13.self_attn.k_proj", "model.layers.13.self_attn.o_proj", "model.layers.13.self_attn.q_proj", "model.layers.13.self_attn.v_proj", "model.layers.14.self_attn.k_proj", "model.layers.14.self_attn.o_proj", "model.layers.14.self_attn.q_proj", "model.layers.14.self_attn.v_proj", "model.layers.15.self_attn.k_proj", "model.layers.15.self_attn.o_proj", "model.layers.15.self_attn.q_proj", "model.layers.15.self_attn.v_proj", "model.layers.16.self_attn.k_proj", "model.layers.16.self_attn.o_proj", "model.layers.16.self_attn.q_proj", "model.layers.16.self_attn.v_proj", "model.layers.17.self_attn.k_proj", "model.layers.17.self_attn.o_proj", "model.layers.17.self_attn.q_proj", "model.layers.17.self_attn.v_proj", "model.layers.18.self_attn.k_proj", "model.layers.18.self_attn.o_proj", "model.layers.18.self_attn.q_proj", "model.layers.18.self_attn.v_proj", "model.layers.19.self_attn.k_proj", "model.layers.19.self_attn.o_proj", "model.layers.19.self_attn.q_proj", "model.layers.19.self_attn.v_proj", "model.layers.2.self_attn.k_proj", "model.layers.2.self_attn.o_proj", "model.layers.2.self_attn.q_proj", "model.layers.2.self_attn.v_proj", "model.layers.20.self_attn.k_proj", "model.layers.20.self_attn.o_proj", "model.layers.20.self_attn.q_proj", "model.layers.20.self_attn.v_proj", "model.layers.21.self_attn.k_proj", "model.layers.21.self_attn.o_proj", "model.layers.21.self_attn.q_proj", "model.layers.21.self_attn.v_proj", "model.layers.22.self_attn.k_proj", "model.layers.22.self_attn.o_proj", "model.layers.22.self_attn.q_proj", "model.layers.22.self_attn.v_proj", "model.layers.23.self_attn.k_proj", "model.layers.23.self_attn.o_proj", "model.layers.23.self_attn.q_proj", "model.layers.23.self_attn.v_proj", "model.layers.24.self_attn.k_proj", "model.layers.24.self_attn.o_proj", "model.layers.24.self_attn.q_proj", "model.layers.24.self_attn.v_proj", "model.layers.25.self_attn.k_proj", "model.layers.25.self_attn.o_proj", "model.layers.25.self_attn.q_proj", "model.layers.25.self_attn.v_proj", "model.layers.26.self_attn.k_proj", "model.layers.26.self_attn.o_proj", "model.layers.26.self_attn.q_proj", "model.layers.26.self_attn.v_proj", "model.layers.27.self_attn.k_proj", "model.layers.27.self_attn.o_proj", "model.layers.27.self_attn.q_proj", "model.layers.27.self_attn.v_proj", "model.layers.28.self_attn.k_proj", "model.layers.28.self_attn.o_proj", "model.layers.28.self_attn.q_proj", "model.layers.28.self_attn.v_proj", "model.layers.29.self_attn.k_proj", "model.layers.29.self_attn.o_proj", "model.layers.29.self_attn.q_proj", "model.layers.29.self_attn.v_proj", "model.layers.3.self_attn.k_proj", "model.layers.3.self_attn.o_proj", "model.layers.3.self_attn.q_proj", "model.layers.3.self_attn.v_proj", "model.layers.4.self_attn.k_proj", "model.layers.4.self_attn.o_proj", "model.layers.4.self_attn.q_proj", "model.layers.4.self_attn.v_proj", "model.layers.5.self_attn.k_proj", "model.layers.5.self_attn.o_proj", "model.layers.5.self_attn.q_proj", "model.layers.5.self_attn.v_proj", "model.layers.6.self_attn.k_proj", "model.layers.6.self_attn.o_proj", "model.layers.6.self_attn.q_proj", "model.layers.6.self_attn.v_proj", "model.layers.7.self_attn.k_proj", "model.layers.7.self_attn.o_proj", "model.layers.7.self_attn.q_proj", "model.layers.7.self_attn.v_proj", "model.layers.8.self_attn.k_proj", "model.layers.8.self_attn.o_proj", "model.layers.8.self_attn.q_proj", "model.layers.8.self_attn.v_proj", "model.layers.9.self_attn.k_proj", "model.layers.9.self_attn.o_proj", "model.layers.9.self_attn.q_proj", "model.layers.9.self_attn.v_proj" ] }, "group_1": { "input_activations": { "dynamic": false, "num_bits": 4, "type": "float", "group_size": 16 }, "weights": { "dynamic": false, "num_bits": 4, "type": "float", "group_size": 16 }, "targets": [ "model.layers.10.mlp.down_proj", "model.layers.10.mlp.gate_proj", "model.layers.10.mlp.up_proj", "model.layers.11.mlp.down_proj", "model.layers.11.mlp.gate_proj", "model.layers.11.mlp.up_proj", "model.layers.12.mlp.down_proj", "model.layers.12.mlp.gate_proj", "model.layers.12.mlp.up_proj", "model.layers.13.mlp.down_proj", "model.layers.13.mlp.gate_proj", "model.layers.13.mlp.up_proj", "model.layers.14.mlp.down_proj", "model.layers.14.mlp.gate_proj", "model.layers.14.mlp.up_proj", "model.layers.15.mlp.down_proj", "model.layers.15.mlp.gate_proj", "model.layers.15.mlp.up_proj", "model.layers.16.mlp.down_proj", "model.layers.16.mlp.gate_proj", "model.layers.16.mlp.up_proj", "model.layers.17.mlp.down_proj", "model.layers.17.mlp.gate_proj", "model.layers.17.mlp.up_proj", "model.layers.18.mlp.down_proj", "model.layers.18.mlp.gate_proj", "model.layers.18.mlp.up_proj", "model.layers.19.mlp.down_proj", "model.layers.19.mlp.gate_proj", "model.layers.19.mlp.up_proj", "model.layers.2.mlp.down_proj", "model.layers.2.mlp.gate_proj", "model.layers.2.mlp.up_proj", "model.layers.20.mlp.down_proj", "model.layers.20.mlp.gate_proj", "model.layers.20.mlp.up_proj", "model.layers.21.mlp.down_proj", "model.layers.21.mlp.gate_proj", "model.layers.21.mlp.up_proj", "model.layers.22.mlp.down_proj", "model.layers.22.mlp.gate_proj", "model.layers.22.mlp.up_proj", "model.layers.23.mlp.down_proj", "model.layers.23.mlp.gate_proj", "model.layers.23.mlp.up_proj", "model.layers.24.mlp.down_proj", "model.layers.24.mlp.gate_proj", "model.layers.24.mlp.up_proj", "model.layers.25.mlp.down_proj", "model.layers.25.mlp.gate_proj", "model.layers.25.mlp.up_proj", "model.layers.26.mlp.down_proj", "model.layers.26.mlp.gate_proj", "model.layers.26.mlp.up_proj", "model.layers.27.mlp.down_proj", "model.layers.27.mlp.gate_proj", "model.layers.27.mlp.up_proj", "model.layers.28.mlp.down_proj", "model.layers.28.mlp.gate_proj", "model.layers.28.mlp.up_proj", "model.layers.29.mlp.down_proj", "model.layers.29.mlp.gate_proj", "model.layers.29.mlp.up_proj", "model.layers.3.mlp.down_proj", "model.layers.3.mlp.gate_proj", "model.layers.3.mlp.up_proj", "model.layers.4.mlp.down_proj", "model.layers.4.mlp.gate_proj", "model.layers.4.mlp.up_proj", "model.layers.5.mlp.down_proj", "model.layers.5.mlp.gate_proj", "model.layers.5.mlp.up_proj", "model.layers.6.mlp.down_proj", "model.layers.6.mlp.gate_proj", "model.layers.6.mlp.up_proj", "model.layers.7.mlp.down_proj", "model.layers.7.mlp.gate_proj", "model.layers.7.mlp.up_proj", "model.layers.8.mlp.down_proj", "model.layers.8.mlp.gate_proj", "model.layers.8.mlp.up_proj", "model.layers.9.mlp.down_proj", "model.layers.9.mlp.gate_proj", "model.layers.9.mlp.up_proj" ] } }, "quantized_layers": { "model.layers.2.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.2.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.2.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.2.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.2.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.2.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.2.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.3.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.3.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.3.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.3.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.3.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.3.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.3.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.4.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.4.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.4.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.4.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.4.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.4.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.4.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.5.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.5.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.5.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.5.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.5.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.5.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.5.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.6.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.6.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.6.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.6.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.6.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.6.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.6.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.7.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.7.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.7.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.7.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.7.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.7.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.7.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.8.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.8.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.8.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.8.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.8.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.8.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.8.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.9.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.9.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.9.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.9.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.9.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.9.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.9.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.10.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.10.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.10.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.10.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.10.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.10.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.10.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.11.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.11.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.11.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.11.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.11.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.11.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.11.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.12.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.12.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.12.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.12.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.12.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.12.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.12.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.13.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.13.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.13.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.13.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.13.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.13.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.13.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.14.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.14.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.14.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.14.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.14.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.14.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.14.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.15.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.15.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.15.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.15.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.15.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.15.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.15.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.16.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.16.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.16.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.16.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.16.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.16.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.16.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.17.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.17.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.17.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.17.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.17.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.17.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.17.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.18.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.18.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.18.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.18.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.18.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.18.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.18.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.19.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.19.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.19.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.19.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.19.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.19.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.19.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.20.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.20.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.20.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.20.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.20.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.20.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.20.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.21.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.21.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.21.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.21.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.21.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.21.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.21.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.22.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.22.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.22.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.22.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.22.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.22.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.22.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.23.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.23.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.23.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.23.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.23.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.23.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.23.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.24.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.24.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.24.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.24.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.24.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.24.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.24.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.25.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.25.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.25.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.25.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.25.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.25.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.25.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.26.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.26.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.26.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.26.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.26.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.26.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.26.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.27.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.27.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.27.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.27.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.27.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.27.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.27.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.28.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.28.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.28.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.28.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.28.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.28.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.28.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.29.self_attn.q_proj": { "quant_algo": "FP8" }, "model.layers.29.self_attn.k_proj": { "quant_algo": "FP8" }, "model.layers.29.self_attn.v_proj": { "quant_algo": "FP8" }, "model.layers.29.self_attn.o_proj": { "quant_algo": "FP8" }, "model.layers.29.mlp.gate_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.29.mlp.up_proj": { "quant_algo": "NVFP4", "group_size": 16 }, "model.layers.29.mlp.down_proj": { "quant_algo": "NVFP4", "group_size": 16 } }, "ignore": [], "quant_algo": "MIXED_PRECISION", "producer": { "name": "modelopt", "version": "0.45.0" }, "quant_method": "modelopt" } }