{ "metadata": { "total_size": 5620074496 }, "weight_map": { "moe.encoder.layers.0.linear1.bias": "model-00001-of-00002.safetensors", "moe.encoder.layers.0.linear1.weight": "model-00001-of-00002.safetensors", "moe.encoder.layers.0.linear2.bias": "model-00001-of-00002.safetensors", "moe.encoder.layers.0.linear2.weight": "model-00001-of-00002.safetensors", "moe.encoder.layers.0.norm1.bias": "model-00001-of-00002.safetensors", "moe.encoder.layers.0.norm1.weight": "model-00001-of-00002.safetensors", "moe.encoder.layers.0.norm2.bias": "model-00001-of-00002.safetensors", "moe.encoder.layers.0.norm2.weight": "model-00001-of-00002.safetensors", "moe.encoder.layers.0.self_attn.in_proj_bias": "model-00001-of-00002.safetensors", "moe.encoder.layers.0.self_attn.in_proj_weight": "model-00001-of-00002.safetensors", "moe.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "moe.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "moe.encoder.layers.1.linear1.bias": "model-00001-of-00002.safetensors", "moe.encoder.layers.1.linear1.weight": "model-00001-of-00002.safetensors", "moe.encoder.layers.1.linear2.bias": "model-00001-of-00002.safetensors", "moe.encoder.layers.1.linear2.weight": "model-00001-of-00002.safetensors", "moe.encoder.layers.1.norm1.bias": "model-00001-of-00002.safetensors", "moe.encoder.layers.1.norm1.weight": "model-00001-of-00002.safetensors", "moe.encoder.layers.1.norm2.bias": "model-00001-of-00002.safetensors", "moe.encoder.layers.1.norm2.weight": "model-00001-of-00002.safetensors", "moe.encoder.layers.1.self_attn.in_proj_bias": "model-00001-of-00002.safetensors", "moe.encoder.layers.1.self_attn.in_proj_weight": "model-00001-of-00002.safetensors", "moe.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "moe.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "moe.mlp_1.bias": "model-00001-of-00002.safetensors", "moe.mlp_1.weight": "model-00001-of-00002.safetensors", "moe.mlp_2.bias": "model-00001-of-00002.safetensors", "moe.mlp_2.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.0.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.0.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.0.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.0.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.0.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.0.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.0.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.0.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.0.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.0.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.1.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.1.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.1.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.1.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.1.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.1.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.1.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.1.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.1.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.1.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.2.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.2.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.2.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.2.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.2.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.2.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.2.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.2.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.2.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.2.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.3.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.3.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.3.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.3.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.3.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.3.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.3.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.3.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.3.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.3.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.mlp_1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.mlp_1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.mlp_2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_bpo.mlp_2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.0.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.0.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.0.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.0.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.0.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.0.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.0.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.0.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.0.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.0.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.1.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.1.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.1.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.1.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.1.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.1.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.1.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.1.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.1.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.1.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.2.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.2.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.2.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.2.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.2.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.2.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.2.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.2.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.2.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.2.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.3.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.3.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.3.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.3.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.3.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.3.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.3.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.3.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.3.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.3.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.mlp_1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.mlp_1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.mlp_2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_cco.mlp_2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.0.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.0.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.0.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.0.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.0.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.0.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.0.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.0.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.0.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.0.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.1.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.1.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.1.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.1.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.1.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.1.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.1.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.1.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.1.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.1.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.mlp_1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.mlp_1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.mlp_2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_ec.mlp_2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.0.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.0.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.0.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.0.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.0.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.0.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.0.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.0.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.0.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.0.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.1.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.1.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.1.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.1.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.1.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.1.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.1.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.1.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.1.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.1.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.mlp_1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.mlp_1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.mlp_2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_gene3D.mlp_2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.0.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.0.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.0.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.0.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.0.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.0.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.0.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.0.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.0.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.0.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.1.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.1.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.1.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.1.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.1.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.1.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.1.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.1.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.1.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.1.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.2.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.2.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.2.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.2.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.2.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.2.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.2.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.2.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.2.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.2.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.3.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.3.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.3.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.3.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.3.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.3.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.3.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.3.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.3.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.3.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.mlp_1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.mlp_1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.mlp_2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_mfo.mlp_2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.0.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.0.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.0.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.0.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.0.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.0.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.0.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.0.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.0.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.0.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.1.linear1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.1.linear1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.1.linear2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.1.linear2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.1.norm1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.1.norm1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.1.norm2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.1.norm2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.1.self_attn.in_proj_bias": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.1.self_attn.in_proj_weight": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.mlp_1.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.mlp_1.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.mlp_2.bias": "model-00002-of-00002.safetensors", "moe.model_aspect_pfam.mlp_2.weight": "model-00002-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.0.linear1.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.0.linear1.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.0.linear2.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.0.linear2.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.0.norm1.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.0.norm1.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.0.norm2.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.0.norm2.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.0.self_attn.in_proj_bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.0.self_attn.in_proj_weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.1.linear1.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.1.linear1.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.1.linear2.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.1.linear2.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.1.norm1.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.1.norm1.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.1.norm2.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.1.norm2.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.1.self_attn.in_proj_bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.1.self_attn.in_proj_weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.2.linear1.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.2.linear1.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.2.linear2.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.2.linear2.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.2.norm1.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.2.norm1.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.2.norm2.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.2.norm2.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.2.self_attn.in_proj_bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.2.self_attn.in_proj_weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.3.linear1.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.3.linear1.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.3.linear2.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.3.linear2.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.3.norm1.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.3.norm1.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.3.norm2.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.3.norm2.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.3.self_attn.in_proj_bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.3.self_attn.in_proj_weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.mlp.bias": "model-00001-of-00002.safetensors", "moe.model_aspect_tmvec.mlp.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.0.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.1.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.10.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.11.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.12.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.13.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.14.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.15.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.16.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.17.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.18.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.19.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.2.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.20.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.20.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.20.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.21.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.21.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.21.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.21.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.21.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.22.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.22.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.22.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.22.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.22.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.23.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.23.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.23.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.23.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.23.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.23.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.23.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.3.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.4.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.5.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.6.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.7.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.8.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.9.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors", "t5.encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors", "t5.encoder.final_layer_norm.weight": "model-00001-of-00002.safetensors", "t5.shared.weight": "model-00001-of-00002.safetensors" } }