{ "metadata": { "total_parameters": 4987310726, "total_size": 19949242904 }, "weight_map": { "decoder.condition_embedder.bias": "model-00004-of-00004.safetensors", "decoder.condition_embedder.weight": "model-00004-of-00004.safetensors", "decoder.layers.0.cross_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.cross_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.cross_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.cross_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.cross_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.cross_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.cross_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.mlp_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.scale_shift_table": "model-00001-of-00004.safetensors", "decoder.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.0.self_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.cross_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.cross_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.cross_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.cross_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.cross_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.cross_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.cross_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.mlp_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.scale_shift_table": "model-00001-of-00004.safetensors", "decoder.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.1.self_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.10.cross_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.cross_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.cross_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.cross_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.cross_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.cross_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.cross_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.mlp_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.scale_shift_table": "model-00002-of-00004.safetensors", "decoder.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.10.self_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.cross_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.cross_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.cross_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.cross_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.cross_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.cross_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.cross_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.mlp_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.scale_shift_table": "model-00002-of-00004.safetensors", "decoder.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.11.self_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.cross_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.cross_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.cross_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.cross_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.cross_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.cross_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.cross_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.mlp_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.scale_shift_table": "model-00002-of-00004.safetensors", "decoder.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.12.self_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.cross_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.cross_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.cross_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.cross_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.cross_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.cross_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.cross_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.mlp_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.scale_shift_table": "model-00002-of-00004.safetensors", "decoder.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.13.self_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.cross_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.cross_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.cross_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.cross_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.cross_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.cross_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.cross_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.mlp_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.scale_shift_table": "model-00002-of-00004.safetensors", "decoder.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.14.self_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.cross_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.cross_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.cross_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.cross_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.cross_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.cross_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.cross_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.mlp_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.scale_shift_table": "model-00002-of-00004.safetensors", "decoder.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.15.self_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.cross_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.cross_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.cross_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.cross_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.cross_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.cross_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.cross_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.mlp_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.scale_shift_table": "model-00002-of-00004.safetensors", "decoder.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.16.self_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.cross_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.cross_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.cross_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.cross_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.cross_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.cross_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.cross_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.mlp_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.scale_shift_table": "model-00002-of-00004.safetensors", "decoder.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.17.self_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.cross_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.cross_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.cross_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.cross_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.cross_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.cross_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.cross_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.mlp_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.scale_shift_table": "model-00002-of-00004.safetensors", "decoder.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.18.self_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.cross_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.cross_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.cross_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.cross_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.cross_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.cross_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.cross_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.19.mlp_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.scale_shift_table": "model-00002-of-00004.safetensors", "decoder.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.19.self_attn_norm.weight": "model-00002-of-00004.safetensors", "decoder.layers.2.cross_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.cross_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.cross_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.cross_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.cross_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.cross_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.cross_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.mlp_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.scale_shift_table": "model-00001-of-00004.safetensors", "decoder.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.2.self_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.20.cross_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.cross_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.cross_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.cross_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.cross_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.cross_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.cross_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.mlp_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.scale_shift_table": "model-00003-of-00004.safetensors", "decoder.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.20.self_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.cross_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.cross_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.cross_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.cross_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.cross_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.cross_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.cross_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.mlp_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.scale_shift_table": "model-00003-of-00004.safetensors", "decoder.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.21.self_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.cross_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.cross_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.cross_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.cross_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.cross_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.cross_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.cross_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.mlp_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.scale_shift_table": "model-00003-of-00004.safetensors", "decoder.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.22.self_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.cross_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.cross_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.cross_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.cross_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.cross_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.cross_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.cross_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.mlp_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.scale_shift_table": "model-00003-of-00004.safetensors", "decoder.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.23.self_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.cross_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.cross_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.cross_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.cross_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.cross_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.cross_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.cross_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.mlp_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.scale_shift_table": "model-00003-of-00004.safetensors", "decoder.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.24.self_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.cross_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.cross_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.cross_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.cross_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.cross_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.cross_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.cross_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.mlp_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.scale_shift_table": "model-00003-of-00004.safetensors", "decoder.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.25.self_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.cross_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.cross_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.cross_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.cross_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.cross_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.cross_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.cross_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.mlp_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.scale_shift_table": "model-00003-of-00004.safetensors", "decoder.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.26.self_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.cross_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.cross_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.cross_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.cross_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.cross_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.cross_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.cross_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.mlp_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.scale_shift_table": "model-00003-of-00004.safetensors", "decoder.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.27.self_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.cross_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.cross_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.cross_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.cross_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.cross_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.cross_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.cross_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.mlp_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.scale_shift_table": "model-00003-of-00004.safetensors", "decoder.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.28.self_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.29.cross_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.29.cross_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.29.cross_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.29.cross_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.29.cross_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.29.cross_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.29.cross_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.29.mlp_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.29.scale_shift_table": "model-00003-of-00004.safetensors", "decoder.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "decoder.layers.29.self_attn_norm.weight": "model-00003-of-00004.safetensors", "decoder.layers.3.cross_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.cross_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.cross_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.cross_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.cross_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.cross_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.cross_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.mlp_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.scale_shift_table": "model-00001-of-00004.safetensors", "decoder.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.3.self_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.30.cross_attn.k_norm.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.cross_attn.k_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.cross_attn.o_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.cross_attn.q_norm.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.cross_attn.q_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.cross_attn.v_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.cross_attn_norm.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.mlp_norm.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.scale_shift_table": "model-00004-of-00004.safetensors", "decoder.layers.30.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.30.self_attn_norm.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.cross_attn.k_norm.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.cross_attn.k_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.cross_attn.o_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.cross_attn.q_norm.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.cross_attn.q_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.cross_attn.v_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.cross_attn_norm.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.mlp_norm.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.scale_shift_table": "model-00004-of-00004.safetensors", "decoder.layers.31.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "decoder.layers.31.self_attn_norm.weight": "model-00004-of-00004.safetensors", "decoder.layers.4.cross_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.cross_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.cross_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.cross_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.cross_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.cross_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.cross_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.mlp_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.scale_shift_table": "model-00001-of-00004.safetensors", "decoder.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.4.self_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.cross_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.cross_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.cross_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.cross_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.cross_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.cross_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.cross_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.mlp_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.scale_shift_table": "model-00001-of-00004.safetensors", "decoder.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.5.self_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.cross_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.cross_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.cross_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.cross_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.cross_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.cross_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.cross_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.mlp_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.scale_shift_table": "model-00001-of-00004.safetensors", "decoder.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.6.self_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.cross_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.cross_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.cross_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.cross_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.cross_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.cross_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.cross_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.mlp_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.scale_shift_table": "model-00001-of-00004.safetensors", "decoder.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.7.self_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.cross_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.cross_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.cross_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.cross_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.cross_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.cross_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.cross_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.mlp_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.scale_shift_table": "model-00001-of-00004.safetensors", "decoder.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.8.self_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.cross_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.cross_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.cross_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.cross_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.cross_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.cross_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.cross_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "decoder.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.mlp_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.scale_shift_table": "model-00001-of-00004.safetensors", "decoder.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "decoder.layers.9.self_attn_norm.weight": "model-00001-of-00004.safetensors", "decoder.norm_out.weight": "model-00004-of-00004.safetensors", "decoder.proj_in.1.bias": "model-00004-of-00004.safetensors", "decoder.proj_in.1.weight": "model-00004-of-00004.safetensors", "decoder.proj_out.1.bias": "model-00004-of-00004.safetensors", "decoder.proj_out.1.weight": "model-00004-of-00004.safetensors", "decoder.scale_shift_table": "model-00001-of-00004.safetensors", "decoder.time_embed.linear_1.bias": "model-00004-of-00004.safetensors", "decoder.time_embed.linear_1.weight": "model-00004-of-00004.safetensors", "decoder.time_embed.linear_2.bias": "model-00004-of-00004.safetensors", "decoder.time_embed.linear_2.weight": "model-00004-of-00004.safetensors", "decoder.time_embed.time_proj.bias": "model-00004-of-00004.safetensors", "decoder.time_embed.time_proj.weight": "model-00004-of-00004.safetensors", "decoder.time_embed_r.linear_1.bias": "model-00004-of-00004.safetensors", "decoder.time_embed_r.linear_1.weight": "model-00004-of-00004.safetensors", "decoder.time_embed_r.linear_2.bias": "model-00004-of-00004.safetensors", "decoder.time_embed_r.linear_2.weight": "model-00004-of-00004.safetensors", "decoder.time_embed_r.time_proj.bias": "model-00004-of-00004.safetensors", "decoder.time_embed_r.time_proj.weight": "model-00004-of-00004.safetensors", "detokenizer.embed_tokens.bias": "model-00004-of-00004.safetensors", "detokenizer.embed_tokens.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.0.input_layernorm.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.0.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.0.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.0.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.1.input_layernorm.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.1.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.1.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "detokenizer.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "detokenizer.norm.weight": "model-00004-of-00004.safetensors", "detokenizer.proj_out.bias": "model-00004-of-00004.safetensors", "detokenizer.proj_out.weight": "model-00004-of-00004.safetensors", "detokenizer.special_tokens": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.embed_tokens.bias": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.embed_tokens.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.0.input_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.0.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.0.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.0.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.1.input_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.1.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.1.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.2.input_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.2.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.2.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.2.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.2.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.2.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.2.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.2.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.3.input_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.3.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.3.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.3.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.3.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.3.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.3.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.4.input_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.4.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.4.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.4.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.4.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.4.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.4.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.4.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.5.input_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.5.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.5.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.5.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.5.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.5.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.5.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.5.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.6.input_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.6.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.6.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.6.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.6.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.6.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.6.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.6.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.7.input_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.7.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.7.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "encoder.lyric_encoder.norm.weight": "model-00004-of-00004.safetensors", "encoder.text_projector.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.embed_tokens.bias": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.embed_tokens.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.0.input_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.0.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.0.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.0.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.1.input_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.1.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.1.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.2.input_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.2.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.2.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.2.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.2.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.2.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.2.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.2.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.3.input_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.3.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.3.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.3.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.3.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.3.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.3.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.norm.weight": "model-00004-of-00004.safetensors", "encoder.timbre_encoder.special_token": "model-00004-of-00004.safetensors", "null_condition_emb": "model-00001-of-00004.safetensors", "tokenizer.attention_pooler.embed_tokens.bias": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.embed_tokens.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.0.input_layernorm.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.0.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.0.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.0.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.1.input_layernorm.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.1.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.1.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.norm.weight": "model-00004-of-00004.safetensors", "tokenizer.attention_pooler.special_token": "model-00004-of-00004.safetensors", "tokenizer.audio_acoustic_proj.bias": "model-00004-of-00004.safetensors", "tokenizer.audio_acoustic_proj.weight": "model-00004-of-00004.safetensors", "tokenizer.quantizer.project_in.bias": "model-00004-of-00004.safetensors", "tokenizer.quantizer.project_in.weight": "model-00004-of-00004.safetensors", "tokenizer.quantizer.project_out.bias": "model-00004-of-00004.safetensors", "tokenizer.quantizer.project_out.weight": "model-00004-of-00004.safetensors" } }