neuralmagic

/

gemma-2-9b-it-FP8

like 5

RuntimeError: Some weights are not initialized from checkpoints: {'model.layers.32.self_attn.attn.v_scale', 'model.layers.13.self_attn.attn.k_scale', 'model.layers.20.self_attn.attn.k_scale', 'model.layers.40.self_attn.attn.v_scale', 'model.layers.10.self_attn.attn.v_scale', 'model.layers.10.self_attn.attn.k_scale', 'model.layers.34.self_attn.attn.v_scale', 'model.layers.17.self_attn.attn.v_scale', 'model.layers.0.self_attn.attn.v_scale', 'model.layers.28.self_attn.attn.k_scale', 'model.layers.23.self_attn.attn.k_scale', 'model.layers.31.self_attn.attn.k_scale', 'model.layers.5.self_attn.attn.k_scale', 'model.layers.8.self_attn.attn.v_scale', 'model.layers.41.self_attn.attn.k_scale', 'model.layers.30.self_attn.attn.v_scale', 'model.layers.0.self_attn.attn.k_scale', 'model.layers.19.self_attn.attn.k_scale', 'model.layers.14.self_attn.attn.k_scale', 'model.layers.24.self_attn.attn.k_scale', 'model.layers.36.self_attn.attn.k_scale', 'model.layers.15.self_attn.attn.v_scale', 'model.layers.12.self_attn.attn.v_scale', 'model.layers.8.self_attn.attn.k_scale', 'model.layers.21.self_attn.attn.v_scale', 'model.layers.20.self_attn.attn.v_scale', 'model.layers.28.self_attn.attn.v_scale', 'model.layers.12.self_attn.attn.k_scale', 'model.layers.9.self_attn.attn.v_scale', 'model.layers.32.self_attn.attn.k_scale', 'model.layers.35.self_attn.attn.v_scale', 'model.layers.24.self_attn.attn.v_scale', 'model.layers.16.self_attn.attn.k_scale', 'model.layers.18.self_attn.attn.k_scale', 'model.layers.31.self_attn.attn.v_scale', 'model.layers.41.self_attn.attn.v_scale', 'model.layers.34.self_attn.attn.k_scale', 'model.layers.9.self_attn.attn.k_scale', 'model.layers.27.self_attn.attn.v_scale', 'model.layers.36.self_attn.attn.v_scale', 'model.layers.22.self_attn.attn.v_scale', 'model.layers.11.self_attn.attn.v_scale', 'model.layers.30.self_attn.attn.k_scale', 'model.layers.29.self_attn.attn.v_scale', 'model.layers.6.self_attn.attn.v_scale', 'model.layers.37.self_attn.attn.k_scale', 'model.layers.38.self_attn.attn.k_scale', 'model.layers.25.self_attn.attn.v_scale', 'model.layers.7.self_attn.attn.v_scale', 'model.layers.1.self_attn.attn.k_scale', 'model.layers.21.self_attn.attn.k_scale', 'model.layers.27.self_attn.attn.k_scale', 'model.layers.2.self_attn.attn.k_scale', 'model.layers.15.self_attn.attn.k_scale', 'model.layers.22.self_attn.attn.k_scale', 'model.layers.18.self_attn.attn.v_scale', 'model.layers.6.self_attn.attn.k_scale', 'model.layers.38.self_attn.attn.v_scale', 'model.layers.37.self_attn.attn.v_scale', 'model.layers.3.self_attn.attn.k_scale', 'model.layers.5.self_attn.attn.v_scale', 'model.layers.23.self_attn.attn.v_scale', 'model.layers.19.self_attn.attn.v_scale', 'model.layers.17.self_attn.attn.k_scale', 'model.layers.35.self_attn.attn.k_scale', 'model.layers.25.self_attn.attn.k_scale', 'model.layers.16.self_attn.attn.v_scale', 'model.layers.7.self_attn.attn.k_scale', 'model.layers.11.self_attn.attn.k_scale', 'model.layers.4.self_attn.attn.k_scale', 'model.layers.40.self_attn.attn.k_scale', 'model.layers.14.self_attn.attn.v_scale', 'model.layers.1.self_attn.attn.v_scale', 'model.layers.39.self_attn.attn.v_scale', 'model.layers.29.self_attn.attn.k_scale', 'model.layers.39.self_attn.attn.k_scale', 'model.layers.26.self_attn.attn.v_scale', 'model.layers.3.self_attn.attn.v_scale', 'model.layers.33.self_attn.attn.k_scale', 'model.layers.13.self_attn.attn.v_scale', 'model.layers.2.self_attn.attn.v_scale', 'model.layers.4.self_attn.attn.v_scale', 'model.layers.33.self_attn.attn.v_scale', 'model.layers.26.self_attn.attn.k_scale'}