{ "add_skip_keys": false, "dequantize_fp32": false, "dynamic_loss_threshold": 0.0002, "group_size": -1, "is_integer": true, "is_training": false, "modules_dtype_dict": { "float8_e3m4fn": [ "model.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight", "model.language_model.layers.17.self_attn.k_proj.weight", "model.language_model.layers.25.mlp.down_proj.weight", "model.language_model.layers.26.mlp.down_proj.weight", "model.language_model.layers.46.mlp.down_proj.weight" ], "int8": [ "model.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight", "model.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight", "model.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight", "model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight", "model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight", "model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight", "model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight", "model.language_model.layers.0.mlp.down_proj.weight", "model.language_model.layers.0.mlp.gate_proj.weight", "model.language_model.layers.0.mlp.up_proj.weight", "model.language_model.layers.0.self_attn.k_proj.weight", "model.language_model.layers.0.self_attn.o_proj.weight", "model.language_model.layers.0.self_attn.q_proj.weight", "model.language_model.layers.0.self_attn.v_proj.weight", "model.language_model.layers.1.self_attn.q_proj.weight", "model.language_model.layers.1.mlp.down_proj.weight", "model.language_model.layers.1.mlp.gate_proj.weight", "model.language_model.layers.1.mlp.up_proj.weight", "model.language_model.layers.1.self_attn.k_proj.weight", "model.language_model.layers.1.self_attn.o_proj.weight", "model.language_model.layers.1.self_attn.v_proj.weight", "model.language_model.layers.2.mlp.down_proj.weight", "model.language_model.layers.2.mlp.gate_proj.weight", "model.language_model.layers.2.mlp.up_proj.weight", "model.language_model.layers.2.self_attn.k_proj.weight", "model.language_model.layers.2.self_attn.o_proj.weight", "model.language_model.layers.2.self_attn.q_proj.weight", "model.language_model.layers.2.self_attn.v_proj.weight", "model.language_model.layers.3.mlp.down_proj.weight", "model.language_model.layers.3.mlp.gate_proj.weight", "model.language_model.layers.3.mlp.up_proj.weight", "model.language_model.layers.3.self_attn.k_proj.weight", "model.language_model.layers.3.self_attn.o_proj.weight", "model.language_model.layers.3.self_attn.q_proj.weight", "model.language_model.layers.3.self_attn.v_proj.weight", "model.language_model.layers.4.mlp.down_proj.weight", "model.language_model.layers.4.mlp.gate_proj.weight", "model.language_model.layers.4.mlp.up_proj.weight", "model.language_model.layers.4.self_attn.k_proj.weight", "model.language_model.layers.4.self_attn.o_proj.weight", "model.language_model.layers.4.self_attn.q_proj.weight", "model.language_model.layers.4.self_attn.v_proj.weight", "model.language_model.layers.5.mlp.down_proj.weight", "model.language_model.layers.5.mlp.gate_proj.weight", "model.language_model.layers.5.mlp.up_proj.weight", "model.language_model.layers.5.self_attn.k_proj.weight", "model.language_model.layers.5.self_attn.o_proj.weight", "model.language_model.layers.5.self_attn.q_proj.weight", "model.language_model.layers.5.self_attn.v_proj.weight", "model.language_model.layers.6.mlp.gate_proj.weight", "model.language_model.layers.6.self_attn.k_proj.weight", "model.language_model.layers.6.self_attn.o_proj.weight", "model.language_model.layers.6.self_attn.q_proj.weight", "model.language_model.layers.6.self_attn.v_proj.weight", "model.language_model.layers.10.mlp.down_proj.weight", "model.language_model.layers.10.mlp.gate_proj.weight", "model.language_model.layers.10.mlp.up_proj.weight", "model.language_model.layers.10.self_attn.k_proj.weight", "model.language_model.layers.10.self_attn.o_proj.weight", "model.language_model.layers.10.self_attn.q_proj.weight", "model.language_model.layers.10.self_attn.v_proj.weight", "model.language_model.layers.11.mlp.down_proj.weight", "model.language_model.layers.11.mlp.gate_proj.weight", "model.language_model.layers.11.mlp.up_proj.weight", "model.language_model.layers.11.self_attn.k_proj.weight", "model.language_model.layers.11.self_attn.o_proj.weight", "model.language_model.layers.11.self_attn.q_proj.weight", "model.language_model.layers.11.self_attn.v_proj.weight", "model.language_model.layers.6.mlp.down_proj.weight", "model.language_model.layers.6.mlp.up_proj.weight", "model.language_model.layers.7.mlp.down_proj.weight", "model.language_model.layers.7.mlp.gate_proj.weight", "model.language_model.layers.7.mlp.up_proj.weight", "model.language_model.layers.7.self_attn.k_proj.weight", "model.language_model.layers.7.self_attn.o_proj.weight", "model.language_model.layers.7.self_attn.q_proj.weight", "model.language_model.layers.7.self_attn.v_proj.weight", "model.language_model.layers.8.mlp.down_proj.weight", "model.language_model.layers.8.mlp.gate_proj.weight", "model.language_model.layers.8.mlp.up_proj.weight", "model.language_model.layers.8.self_attn.k_proj.weight", "model.language_model.layers.8.self_attn.o_proj.weight", "model.language_model.layers.8.self_attn.q_proj.weight", "model.language_model.layers.8.self_attn.v_proj.weight", "model.language_model.layers.9.mlp.down_proj.weight", "model.language_model.layers.9.mlp.gate_proj.weight", "model.language_model.layers.9.mlp.up_proj.weight", "model.language_model.layers.9.self_attn.k_proj.weight", "model.language_model.layers.9.self_attn.o_proj.weight", "model.language_model.layers.9.self_attn.q_proj.weight", "model.language_model.layers.9.self_attn.v_proj.weight", "model.language_model.layers.12.mlp.down_proj.weight", "model.language_model.layers.12.mlp.gate_proj.weight", "model.language_model.layers.12.mlp.up_proj.weight", "model.language_model.layers.12.self_attn.k_proj.weight", "model.language_model.layers.12.self_attn.o_proj.weight", "model.language_model.layers.12.self_attn.q_proj.weight", "model.language_model.layers.12.self_attn.v_proj.weight", "model.language_model.layers.13.mlp.down_proj.weight", "model.language_model.layers.13.mlp.gate_proj.weight", "model.language_model.layers.13.mlp.up_proj.weight", "model.language_model.layers.13.self_attn.k_proj.weight", "model.language_model.layers.13.self_attn.o_proj.weight", "model.language_model.layers.13.self_attn.q_proj.weight", "model.language_model.layers.13.self_attn.v_proj.weight", "model.language_model.layers.14.mlp.down_proj.weight", "model.language_model.layers.14.mlp.gate_proj.weight", "model.language_model.layers.14.mlp.up_proj.weight", "model.language_model.layers.14.self_attn.k_proj.weight", "model.language_model.layers.14.self_attn.o_proj.weight", "model.language_model.layers.14.self_attn.q_proj.weight", "model.language_model.layers.14.self_attn.v_proj.weight", "model.language_model.layers.15.mlp.down_proj.weight", "model.language_model.layers.15.mlp.gate_proj.weight", "model.language_model.layers.15.mlp.up_proj.weight", "model.language_model.layers.15.self_attn.k_proj.weight", "model.language_model.layers.15.self_attn.o_proj.weight", "model.language_model.layers.15.self_attn.q_proj.weight", "model.language_model.layers.15.self_attn.v_proj.weight", "model.language_model.layers.16.mlp.gate_proj.weight", "model.language_model.layers.16.mlp.up_proj.weight", "model.language_model.layers.16.self_attn.k_proj.weight", "model.language_model.layers.16.self_attn.o_proj.weight", "model.language_model.layers.16.self_attn.q_proj.weight", "model.language_model.layers.16.self_attn.v_proj.weight", "model.language_model.layers.17.mlp.gate_proj.weight", "model.language_model.layers.17.self_attn.o_proj.weight", "model.language_model.layers.17.self_attn.q_proj.weight", "model.language_model.layers.17.self_attn.v_proj.weight", "model.language_model.layers.17.mlp.down_proj.weight", "model.language_model.layers.17.mlp.up_proj.weight", "model.language_model.layers.18.mlp.down_proj.weight", "model.language_model.layers.18.mlp.gate_proj.weight", "model.language_model.layers.18.mlp.up_proj.weight", "model.language_model.layers.18.self_attn.k_proj.weight", "model.language_model.layers.18.self_attn.o_proj.weight", "model.language_model.layers.18.self_attn.q_proj.weight", "model.language_model.layers.18.self_attn.v_proj.weight", "model.language_model.layers.19.mlp.down_proj.weight", "model.language_model.layers.19.mlp.gate_proj.weight", "model.language_model.layers.19.mlp.up_proj.weight", "model.language_model.layers.19.self_attn.k_proj.weight", "model.language_model.layers.19.self_attn.o_proj.weight", "model.language_model.layers.19.self_attn.q_proj.weight", "model.language_model.layers.19.self_attn.v_proj.weight", "model.language_model.layers.20.mlp.down_proj.weight", "model.language_model.layers.20.mlp.gate_proj.weight", "model.language_model.layers.20.mlp.up_proj.weight", "model.language_model.layers.20.self_attn.k_proj.weight", "model.language_model.layers.20.self_attn.o_proj.weight", "model.language_model.layers.20.self_attn.q_proj.weight", "model.language_model.layers.20.self_attn.v_proj.weight", "model.language_model.layers.21.mlp.down_proj.weight", "model.language_model.layers.21.mlp.gate_proj.weight", "model.language_model.layers.21.mlp.up_proj.weight", "model.language_model.layers.21.self_attn.k_proj.weight", "model.language_model.layers.21.self_attn.o_proj.weight", "model.language_model.layers.21.self_attn.q_proj.weight", "model.language_model.layers.21.self_attn.v_proj.weight", "model.language_model.layers.22.mlp.down_proj.weight", "model.language_model.layers.22.mlp.gate_proj.weight", "model.language_model.layers.22.mlp.up_proj.weight", "model.language_model.layers.22.self_attn.k_proj.weight", "model.language_model.layers.22.self_attn.o_proj.weight", "model.language_model.layers.22.self_attn.q_proj.weight", "model.language_model.layers.22.self_attn.v_proj.weight", "model.language_model.layers.23.mlp.down_proj.weight", "model.language_model.layers.23.mlp.gate_proj.weight", "model.language_model.layers.23.mlp.up_proj.weight", "model.language_model.layers.23.self_attn.k_proj.weight", "model.language_model.layers.23.self_attn.o_proj.weight", "model.language_model.layers.23.self_attn.q_proj.weight", "model.language_model.layers.23.self_attn.v_proj.weight", "model.language_model.layers.24.mlp.down_proj.weight", "model.language_model.layers.24.mlp.gate_proj.weight", "model.language_model.layers.24.mlp.up_proj.weight", "model.language_model.layers.24.self_attn.k_proj.weight", "model.language_model.layers.24.self_attn.o_proj.weight", "model.language_model.layers.24.self_attn.q_proj.weight", "model.language_model.layers.24.self_attn.v_proj.weight", "model.language_model.layers.25.mlp.gate_proj.weight", "model.language_model.layers.25.mlp.up_proj.weight", "model.language_model.layers.25.self_attn.k_proj.weight", "model.language_model.layers.25.self_attn.o_proj.weight", "model.language_model.layers.25.self_attn.q_proj.weight", "model.language_model.layers.25.self_attn.v_proj.weight", "model.language_model.layers.26.mlp.gate_proj.weight", "model.language_model.layers.26.mlp.up_proj.weight", "model.language_model.layers.26.self_attn.k_proj.weight", "model.language_model.layers.26.self_attn.o_proj.weight", "model.language_model.layers.26.self_attn.q_proj.weight", "model.language_model.layers.26.self_attn.v_proj.weight", "model.language_model.layers.27.mlp.down_proj.weight", "model.language_model.layers.27.mlp.gate_proj.weight", "model.language_model.layers.27.mlp.up_proj.weight", "model.language_model.layers.27.self_attn.k_proj.weight", "model.language_model.layers.27.self_attn.o_proj.weight", "model.language_model.layers.27.self_attn.q_proj.weight", "model.language_model.layers.27.self_attn.v_proj.weight", "model.language_model.layers.28.mlp.gate_proj.weight", "model.language_model.layers.28.self_attn.k_proj.weight", "model.language_model.layers.28.self_attn.o_proj.weight", "model.language_model.layers.28.self_attn.q_proj.weight", "model.language_model.layers.28.self_attn.v_proj.weight", "model.language_model.layers.28.mlp.down_proj.weight", "model.language_model.layers.28.mlp.up_proj.weight", "model.language_model.layers.29.mlp.down_proj.weight", "model.language_model.layers.29.mlp.gate_proj.weight", "model.language_model.layers.29.mlp.up_proj.weight", "model.language_model.layers.29.self_attn.k_proj.weight", "model.language_model.layers.29.self_attn.o_proj.weight", "model.language_model.layers.29.self_attn.q_proj.weight", "model.language_model.layers.29.self_attn.v_proj.weight", "model.language_model.layers.30.mlp.down_proj.weight", "model.language_model.layers.30.mlp.gate_proj.weight", "model.language_model.layers.30.mlp.up_proj.weight", "model.language_model.layers.30.self_attn.k_proj.weight", "model.language_model.layers.30.self_attn.o_proj.weight", "model.language_model.layers.30.self_attn.q_proj.weight", "model.language_model.layers.30.self_attn.v_proj.weight", "model.language_model.layers.31.mlp.down_proj.weight", "model.language_model.layers.31.mlp.gate_proj.weight", "model.language_model.layers.31.mlp.up_proj.weight", "model.language_model.layers.31.self_attn.k_proj.weight", "model.language_model.layers.31.self_attn.o_proj.weight", "model.language_model.layers.31.self_attn.q_proj.weight", "model.language_model.layers.31.self_attn.v_proj.weight", "model.language_model.layers.32.mlp.down_proj.weight", "model.language_model.layers.32.mlp.gate_proj.weight", "model.language_model.layers.32.mlp.up_proj.weight", "model.language_model.layers.32.self_attn.k_proj.weight", "model.language_model.layers.32.self_attn.o_proj.weight", "model.language_model.layers.32.self_attn.q_proj.weight", "model.language_model.layers.32.self_attn.v_proj.weight", "model.language_model.layers.33.mlp.down_proj.weight", "model.language_model.layers.33.mlp.gate_proj.weight", "model.language_model.layers.33.mlp.up_proj.weight", "model.language_model.layers.33.self_attn.k_proj.weight", "model.language_model.layers.33.self_attn.o_proj.weight", "model.language_model.layers.33.self_attn.q_proj.weight", "model.language_model.layers.33.self_attn.v_proj.weight", "model.language_model.layers.34.mlp.down_proj.weight", "model.language_model.layers.34.mlp.gate_proj.weight", "model.language_model.layers.34.mlp.up_proj.weight", "model.language_model.layers.34.self_attn.k_proj.weight", "model.language_model.layers.34.self_attn.o_proj.weight", "model.language_model.layers.34.self_attn.q_proj.weight", "model.language_model.layers.34.self_attn.v_proj.weight", "model.language_model.layers.35.mlp.down_proj.weight", "model.language_model.layers.35.mlp.gate_proj.weight", "model.language_model.layers.35.mlp.up_proj.weight", "model.language_model.layers.35.self_attn.k_proj.weight", "model.language_model.layers.35.self_attn.o_proj.weight", "model.language_model.layers.35.self_attn.q_proj.weight", "model.language_model.layers.35.self_attn.v_proj.weight", "model.language_model.layers.36.mlp.down_proj.weight", "model.language_model.layers.36.mlp.gate_proj.weight", "model.language_model.layers.36.mlp.up_proj.weight", "model.language_model.layers.36.self_attn.k_proj.weight", "model.language_model.layers.36.self_attn.o_proj.weight", "model.language_model.layers.36.self_attn.q_proj.weight", "model.language_model.layers.36.self_attn.v_proj.weight", "model.language_model.layers.37.mlp.down_proj.weight", "model.language_model.layers.37.mlp.gate_proj.weight", "model.language_model.layers.37.mlp.up_proj.weight", "model.language_model.layers.37.self_attn.k_proj.weight", "model.language_model.layers.37.self_attn.o_proj.weight", "model.language_model.layers.37.self_attn.q_proj.weight", "model.language_model.layers.37.self_attn.v_proj.weight", "model.language_model.layers.38.mlp.down_proj.weight", "model.language_model.layers.38.mlp.gate_proj.weight", "model.language_model.layers.38.mlp.up_proj.weight", "model.language_model.layers.38.self_attn.k_proj.weight", "model.language_model.layers.38.self_attn.o_proj.weight", "model.language_model.layers.38.self_attn.q_proj.weight", "model.language_model.layers.38.self_attn.v_proj.weight", "model.language_model.layers.39.mlp.gate_proj.weight", "model.language_model.layers.39.self_attn.k_proj.weight", "model.language_model.layers.39.self_attn.o_proj.weight", "model.language_model.layers.39.self_attn.q_proj.weight", "model.language_model.layers.39.self_attn.v_proj.weight", "model.language_model.layers.39.mlp.down_proj.weight", "model.language_model.layers.39.mlp.up_proj.weight", "model.language_model.layers.40.mlp.down_proj.weight", "model.language_model.layers.40.mlp.gate_proj.weight", "model.language_model.layers.40.mlp.up_proj.weight", "model.language_model.layers.40.self_attn.k_proj.weight", "model.language_model.layers.40.self_attn.o_proj.weight", "model.language_model.layers.40.self_attn.q_proj.weight", "model.language_model.layers.40.self_attn.v_proj.weight", "model.language_model.layers.41.mlp.down_proj.weight", "model.language_model.layers.41.mlp.gate_proj.weight", "model.language_model.layers.41.mlp.up_proj.weight", "model.language_model.layers.41.self_attn.k_proj.weight", "model.language_model.layers.41.self_attn.o_proj.weight", "model.language_model.layers.41.self_attn.q_proj.weight", "model.language_model.layers.41.self_attn.v_proj.weight", "model.language_model.layers.42.mlp.down_proj.weight", "model.language_model.layers.42.mlp.gate_proj.weight", "model.language_model.layers.42.mlp.up_proj.weight", "model.language_model.layers.42.self_attn.k_proj.weight", "model.language_model.layers.42.self_attn.o_proj.weight", "model.language_model.layers.42.self_attn.q_proj.weight", "model.language_model.layers.42.self_attn.v_proj.weight", "model.language_model.layers.43.mlp.down_proj.weight", "model.language_model.layers.43.mlp.gate_proj.weight", "model.language_model.layers.43.mlp.up_proj.weight", "model.language_model.layers.43.self_attn.k_proj.weight", "model.language_model.layers.43.self_attn.o_proj.weight", "model.language_model.layers.43.self_attn.q_proj.weight", "model.language_model.layers.43.self_attn.v_proj.weight", "model.language_model.layers.44.mlp.down_proj.weight", "model.language_model.layers.44.mlp.gate_proj.weight", "model.language_model.layers.44.mlp.up_proj.weight", "model.language_model.layers.44.self_attn.k_proj.weight", "model.language_model.layers.44.self_attn.o_proj.weight", "model.language_model.layers.44.self_attn.q_proj.weight", "model.language_model.layers.44.self_attn.v_proj.weight", "model.language_model.layers.45.mlp.down_proj.weight", "model.language_model.layers.45.mlp.gate_proj.weight", "model.language_model.layers.45.mlp.up_proj.weight", "model.language_model.layers.45.self_attn.k_proj.weight", "model.language_model.layers.45.self_attn.o_proj.weight", "model.language_model.layers.45.self_attn.q_proj.weight", "model.language_model.layers.45.self_attn.v_proj.weight", "model.language_model.layers.46.mlp.gate_proj.weight", "model.language_model.layers.46.mlp.up_proj.weight", "model.language_model.layers.46.self_attn.k_proj.weight", "model.language_model.layers.46.self_attn.o_proj.weight", "model.language_model.layers.46.self_attn.q_proj.weight", "model.language_model.layers.46.self_attn.v_proj.weight", "model.language_model.layers.47.mlp.gate_proj.weight", "model.language_model.layers.47.mlp.up_proj.weight", "model.language_model.layers.47.self_attn.k_proj.weight", "model.language_model.layers.47.self_attn.o_proj.weight", "model.language_model.layers.47.self_attn.q_proj.weight", "model.language_model.layers.47.self_attn.v_proj.weight" ] }, "modules_to_not_convert": [ "model.language_model.embed_tokens", ".x_embedder", ".t_embedder", "wte", "patch_embedding", ".emb_in", ".context_embedder", ".final_layer", ".time_embed", "lm_head", "lm_head.weight", ".norm_out", "multi_modal_projector", "time_text_embed", "patch_emb", ".emb_out", ".vid_in", ".vid_out", ".img_in", "model.language_model.norm", ".img_out", ".condition_embedder", ".proj_out", ".txt_out", ".txt_in", "patch_embed", ".y_embedder", "model.language_model.layers.16.mlp.down_proj.weight", "model.language_model.layers.47.mlp.down_proj.weight" ], "non_blocking": false, "quant_conv": false, "quant_method": "sdnq", "quantization_device": null, "quantized_matmul_dtype": null, "return_device": null, "sdnq_version": "0.1.4", "svd_rank": 32, "svd_steps": 8, "use_dynamic_quantization": true, "use_grad_ckpt": true, "use_quantized_matmul": false, "use_quantized_matmul_conv": false, "use_static_quantization": true, "use_stochastic_rounding": false, "use_svd": false, "weights_dtype": "int8" }