model.safetensors.index.json

{
  "metadata": {
    "total_size": 28192679936
  },
  "weight_map": {
    "decoder.model.decoder.embed_positions.weight": "model-00002-of-00027.safetensors",
    "decoder.model.decoder.embed_tokens.weight": "model-00001-of-00027.safetensors",
    "decoder.model.decoder.layernorm_embedding.bias": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layernorm_embedding.weight": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.encoder_attn.k_proj.bias": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.fc1.bias": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.fc1.weight": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.fc2.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.0.fc2.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.0.final_layer_norm.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.0.final_layer_norm.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.self_attn_layer_norm.bias": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.0.self_attn_layer_norm.weight": "model-00003-of-00027.safetensors",
    "decoder.model.decoder.layers.1.encoder_attn.k_proj.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.fc1.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.fc1.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.fc2.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.fc2.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.final_layer_norm.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.final_layer_norm.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.self_attn.k_proj.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.self_attn.out_proj.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.self_attn.q_proj.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.self_attn.v_proj.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.self_attn_layer_norm.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.1.self_attn_layer_norm.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.10.encoder_attn.k_proj.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.10.fc1.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.10.fc1.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.10.fc2.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.10.fc2.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.10.final_layer_norm.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.10.final_layer_norm.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.10.self_attn.k_proj.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.10.self_attn.k_proj.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.10.self_attn.out_proj.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.10.self_attn.out_proj.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.10.self_attn.q_proj.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.10.self_attn.q_proj.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.10.self_attn.v_proj.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.10.self_attn.v_proj.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.10.self_attn_layer_norm.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.10.self_attn_layer_norm.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.11.encoder_attn.k_proj.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.fc1.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.fc1.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.fc2.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.fc2.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.final_layer_norm.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.final_layer_norm.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.self_attn.k_proj.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.self_attn.k_proj.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.self_attn.out_proj.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.self_attn.out_proj.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.self_attn.q_proj.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.self_attn.q_proj.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.self_attn.v_proj.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.self_attn.v_proj.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.self_attn_layer_norm.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.11.self_attn_layer_norm.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.12.encoder_attn.k_proj.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.encoder_attn.out_proj.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.encoder_attn.q_proj.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.encoder_attn.v_proj.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.fc1.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.fc1.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.fc2.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.fc2.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.final_layer_norm.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.final_layer_norm.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.self_attn.k_proj.bias": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.12.self_attn.k_proj.weight": "model-00011-of-00027.safetensors",
    "decoder.model.decoder.layers.12.self_attn.out_proj.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.self_attn.out_proj.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.self_attn.q_proj.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.self_attn.q_proj.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.self_attn.v_proj.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.self_attn.v_proj.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.self_attn_layer_norm.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.12.self_attn_layer_norm.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.13.encoder_attn.k_proj.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.13.encoder_attn.out_proj.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.13.encoder_attn.q_proj.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.13.encoder_attn.v_proj.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.13.fc1.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.13.fc1.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.13.fc2.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.13.fc2.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.13.final_layer_norm.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.13.final_layer_norm.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.13.self_attn.k_proj.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.13.self_attn.k_proj.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.13.self_attn.out_proj.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.13.self_attn.out_proj.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.13.self_attn.q_proj.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.13.self_attn.q_proj.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.13.self_attn.v_proj.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.13.self_attn.v_proj.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.13.self_attn_layer_norm.bias": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.13.self_attn_layer_norm.weight": "model-00012-of-00027.safetensors",
    "decoder.model.decoder.layers.14.encoder_attn.k_proj.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.encoder_attn.out_proj.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.encoder_attn.q_proj.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.encoder_attn.v_proj.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.encoder_attn.v_proj.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.encoder_attn_layer_norm.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.encoder_attn_layer_norm.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.fc1.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.fc1.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.fc2.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.14.fc2.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.14.final_layer_norm.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.14.final_layer_norm.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.14.self_attn.k_proj.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.self_attn.k_proj.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.self_attn.out_proj.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.self_attn.out_proj.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.self_attn.q_proj.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.self_attn.q_proj.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.self_attn.v_proj.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.self_attn.v_proj.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.self_attn_layer_norm.bias": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.14.self_attn_layer_norm.weight": "model-00013-of-00027.safetensors",
    "decoder.model.decoder.layers.15.encoder_attn.k_proj.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.encoder_attn.k_proj.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.encoder_attn.out_proj.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.encoder_attn.out_proj.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.encoder_attn.q_proj.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.encoder_attn.q_proj.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.encoder_attn.v_proj.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.encoder_attn.v_proj.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.encoder_attn_layer_norm.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.encoder_attn_layer_norm.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.fc1.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.fc1.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.fc2.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.fc2.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.final_layer_norm.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.final_layer_norm.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.self_attn.k_proj.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.self_attn.k_proj.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.self_attn.out_proj.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.self_attn.out_proj.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.self_attn.q_proj.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.self_attn.q_proj.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.self_attn.v_proj.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.self_attn.v_proj.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.self_attn_layer_norm.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.15.self_attn_layer_norm.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.16.encoder_attn.k_proj.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.encoder_attn.k_proj.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.encoder_attn.out_proj.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.encoder_attn.out_proj.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.encoder_attn.q_proj.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.encoder_attn.q_proj.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.encoder_attn.v_proj.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.encoder_attn.v_proj.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.encoder_attn_layer_norm.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.encoder_attn_layer_norm.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.fc1.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.fc1.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.fc2.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.fc2.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.final_layer_norm.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.final_layer_norm.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.self_attn.k_proj.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.16.self_attn.k_proj.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.16.self_attn.out_proj.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.self_attn.out_proj.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.self_attn.q_proj.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.16.self_attn.q_proj.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.16.self_attn.v_proj.bias": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.16.self_attn.v_proj.weight": "model-00014-of-00027.safetensors",
    "decoder.model.decoder.layers.16.self_attn_layer_norm.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.16.self_attn_layer_norm.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.encoder_attn.k_proj.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.encoder_attn.k_proj.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.encoder_attn.out_proj.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.17.encoder_attn.out_proj.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.17.encoder_attn.q_proj.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.encoder_attn.q_proj.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.encoder_attn.v_proj.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.encoder_attn.v_proj.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.encoder_attn_layer_norm.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.17.encoder_attn_layer_norm.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.17.fc1.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.17.fc1.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.17.fc2.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.17.fc2.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.17.final_layer_norm.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.17.final_layer_norm.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.17.self_attn.k_proj.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.self_attn.k_proj.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.self_attn.out_proj.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.self_attn.out_proj.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.self_attn.q_proj.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.self_attn.q_proj.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.self_attn.v_proj.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.self_attn.v_proj.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.self_attn_layer_norm.bias": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.17.self_attn_layer_norm.weight": "model-00015-of-00027.safetensors",
    "decoder.model.decoder.layers.18.encoder_attn.k_proj.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.encoder_attn.k_proj.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.encoder_attn.out_proj.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.encoder_attn.out_proj.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.encoder_attn.q_proj.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.encoder_attn.q_proj.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.encoder_attn.v_proj.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.encoder_attn.v_proj.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.encoder_attn_layer_norm.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.encoder_attn_layer_norm.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.fc1.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.fc1.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.fc2.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.fc2.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.final_layer_norm.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.final_layer_norm.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.self_attn.k_proj.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.self_attn.k_proj.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.self_attn.out_proj.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.self_attn.out_proj.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.self_attn.q_proj.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.self_attn.q_proj.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.self_attn.v_proj.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.self_attn.v_proj.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.self_attn_layer_norm.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.18.self_attn_layer_norm.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.19.encoder_attn.k_proj.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.encoder_attn.k_proj.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.encoder_attn.out_proj.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.encoder_attn.out_proj.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.encoder_attn.q_proj.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.encoder_attn.q_proj.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.encoder_attn.v_proj.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.encoder_attn.v_proj.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.encoder_attn_layer_norm.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.encoder_attn_layer_norm.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.fc1.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.fc1.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.fc2.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.fc2.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.final_layer_norm.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.final_layer_norm.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.self_attn.k_proj.bias": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.19.self_attn.k_proj.weight": "model-00016-of-00027.safetensors",
    "decoder.model.decoder.layers.19.self_attn.out_proj.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.self_attn.out_proj.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.self_attn.q_proj.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.self_attn.q_proj.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.self_attn.v_proj.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.self_attn.v_proj.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.self_attn_layer_norm.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.19.self_attn_layer_norm.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.2.encoder_attn.k_proj.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.fc1.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.fc1.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.fc2.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.fc2.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.final_layer_norm.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.final_layer_norm.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.self_attn.k_proj.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.2.self_attn.k_proj.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.2.self_attn.out_proj.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.self_attn.out_proj.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.self_attn.q_proj.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.2.self_attn.q_proj.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.2.self_attn.v_proj.bias": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00027.safetensors",
    "decoder.model.decoder.layers.2.self_attn_layer_norm.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.2.self_attn_layer_norm.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.20.encoder_attn.k_proj.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.20.encoder_attn.out_proj.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.20.encoder_attn.q_proj.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.20.encoder_attn.v_proj.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.20.encoder_attn.v_proj.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.20.encoder_attn_layer_norm.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.20.encoder_attn_layer_norm.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.20.fc1.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.20.fc1.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.20.fc2.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.20.fc2.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.20.final_layer_norm.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.20.final_layer_norm.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.20.self_attn.k_proj.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.20.self_attn.k_proj.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.20.self_attn.out_proj.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.20.self_attn.out_proj.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.20.self_attn.q_proj.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.20.self_attn.q_proj.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.20.self_attn.v_proj.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.20.self_attn.v_proj.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.20.self_attn_layer_norm.bias": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.20.self_attn_layer_norm.weight": "model-00017-of-00027.safetensors",
    "decoder.model.decoder.layers.21.encoder_attn.k_proj.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.encoder_attn.k_proj.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.encoder_attn.out_proj.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.encoder_attn.out_proj.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.encoder_attn.q_proj.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.encoder_attn.q_proj.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.encoder_attn.v_proj.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.encoder_attn.v_proj.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.encoder_attn_layer_norm.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.encoder_attn_layer_norm.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.fc1.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.fc1.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.fc2.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.21.fc2.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.21.final_layer_norm.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.21.final_layer_norm.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.21.self_attn.k_proj.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.self_attn.k_proj.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.self_attn.out_proj.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.self_attn.out_proj.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.self_attn.q_proj.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.self_attn.q_proj.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.self_attn.v_proj.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.self_attn.v_proj.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.self_attn_layer_norm.bias": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.21.self_attn_layer_norm.weight": "model-00018-of-00027.safetensors",
    "decoder.model.decoder.layers.22.encoder_attn.k_proj.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.encoder_attn.k_proj.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.encoder_attn.out_proj.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.encoder_attn.out_proj.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.encoder_attn.q_proj.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.encoder_attn.q_proj.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.encoder_attn.v_proj.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.encoder_attn.v_proj.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.encoder_attn_layer_norm.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.encoder_attn_layer_norm.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.fc1.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.fc1.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.fc2.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.fc2.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.final_layer_norm.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.final_layer_norm.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.self_attn.k_proj.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.self_attn.k_proj.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.self_attn.out_proj.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.self_attn.out_proj.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.self_attn.q_proj.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.self_attn.q_proj.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.self_attn.v_proj.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.self_attn.v_proj.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.self_attn_layer_norm.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.22.self_attn_layer_norm.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.23.encoder_attn.k_proj.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.encoder_attn.k_proj.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.encoder_attn.out_proj.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.encoder_attn.out_proj.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.encoder_attn.q_proj.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.encoder_attn.q_proj.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.encoder_attn.v_proj.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.encoder_attn.v_proj.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.encoder_attn_layer_norm.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.encoder_attn_layer_norm.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.fc1.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.fc1.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.fc2.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.fc2.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.final_layer_norm.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.final_layer_norm.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.self_attn.k_proj.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.23.self_attn.k_proj.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.23.self_attn.out_proj.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.self_attn.out_proj.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.self_attn.q_proj.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.23.self_attn.q_proj.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.23.self_attn.v_proj.bias": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.23.self_attn.v_proj.weight": "model-00019-of-00027.safetensors",
    "decoder.model.decoder.layers.23.self_attn_layer_norm.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.23.self_attn_layer_norm.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.encoder_attn.k_proj.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.encoder_attn.k_proj.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.encoder_attn.out_proj.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.24.encoder_attn.out_proj.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.24.encoder_attn.q_proj.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.encoder_attn.q_proj.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.encoder_attn.v_proj.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.encoder_attn.v_proj.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.encoder_attn_layer_norm.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.24.encoder_attn_layer_norm.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.24.fc1.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.24.fc1.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.24.fc2.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.24.fc2.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.24.final_layer_norm.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.24.final_layer_norm.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.24.self_attn.k_proj.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.self_attn.k_proj.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.self_attn.out_proj.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.self_attn.out_proj.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.self_attn.q_proj.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.self_attn.q_proj.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.self_attn.v_proj.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.self_attn.v_proj.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.self_attn_layer_norm.bias": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.24.self_attn_layer_norm.weight": "model-00020-of-00027.safetensors",
    "decoder.model.decoder.layers.25.encoder_attn.k_proj.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.encoder_attn.k_proj.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.encoder_attn.out_proj.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.encoder_attn.out_proj.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.encoder_attn.q_proj.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.encoder_attn.q_proj.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.encoder_attn.v_proj.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.encoder_attn.v_proj.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.encoder_attn_layer_norm.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.encoder_attn_layer_norm.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.fc1.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.fc1.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.fc2.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.fc2.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.final_layer_norm.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.final_layer_norm.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.self_attn.k_proj.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.self_attn.k_proj.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.self_attn.out_proj.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.self_attn.out_proj.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.self_attn.q_proj.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.self_attn.q_proj.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.self_attn.v_proj.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.self_attn.v_proj.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.self_attn_layer_norm.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.25.self_attn_layer_norm.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.26.encoder_attn.k_proj.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.encoder_attn.k_proj.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.encoder_attn.out_proj.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.encoder_attn.out_proj.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.encoder_attn.q_proj.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.encoder_attn.q_proj.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.encoder_attn.v_proj.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.encoder_attn.v_proj.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.encoder_attn_layer_norm.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.encoder_attn_layer_norm.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.fc1.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.fc1.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.fc2.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.fc2.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.final_layer_norm.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.final_layer_norm.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.self_attn.k_proj.bias": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.26.self_attn.k_proj.weight": "model-00021-of-00027.safetensors",
    "decoder.model.decoder.layers.26.self_attn.out_proj.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.self_attn.out_proj.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.self_attn.q_proj.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.self_attn.v_proj.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.self_attn_layer_norm.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.26.self_attn_layer_norm.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.27.encoder_attn.k_proj.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.27.encoder_attn.k_proj.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.27.encoder_attn.out_proj.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.27.encoder_attn.out_proj.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.27.encoder_attn.q_proj.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.27.encoder_attn.q_proj.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.27.encoder_attn.v_proj.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.27.encoder_attn.v_proj.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.27.encoder_attn_layer_norm.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.27.encoder_attn_layer_norm.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.27.fc1.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.27.fc1.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.27.fc2.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.27.fc2.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.27.final_layer_norm.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.27.final_layer_norm.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.27.self_attn.k_proj.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.27.self_attn.k_proj.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.27.self_attn.out_proj.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.27.self_attn.out_proj.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.27.self_attn.q_proj.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.27.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.27.self_attn.v_proj.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.27.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.27.self_attn_layer_norm.bias": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.27.self_attn_layer_norm.weight": "model-00022-of-00027.safetensors",
    "decoder.model.decoder.layers.28.encoder_attn.k_proj.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.encoder_attn.k_proj.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.encoder_attn.out_proj.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.encoder_attn.out_proj.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.encoder_attn.q_proj.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.encoder_attn.q_proj.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.encoder_attn.v_proj.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.encoder_attn.v_proj.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.encoder_attn_layer_norm.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.encoder_attn_layer_norm.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.fc1.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.fc1.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.fc2.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.28.fc2.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.28.final_layer_norm.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.28.final_layer_norm.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.28.self_attn.k_proj.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.self_attn.k_proj.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.self_attn.out_proj.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.self_attn.out_proj.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.self_attn.q_proj.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.self_attn.q_proj.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.self_attn.v_proj.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.self_attn.v_proj.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.self_attn_layer_norm.bias": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.28.self_attn_layer_norm.weight": "model-00023-of-00027.safetensors",
    "decoder.model.decoder.layers.29.encoder_attn.k_proj.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.encoder_attn.k_proj.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.encoder_attn.out_proj.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.encoder_attn.out_proj.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.encoder_attn.q_proj.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.encoder_attn.q_proj.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.encoder_attn.v_proj.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.encoder_attn.v_proj.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.encoder_attn_layer_norm.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.encoder_attn_layer_norm.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.fc1.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.fc1.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.fc2.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.fc2.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.final_layer_norm.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.final_layer_norm.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.self_attn.k_proj.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.self_attn.k_proj.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.self_attn.out_proj.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.self_attn.out_proj.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.self_attn.q_proj.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.self_attn.q_proj.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.self_attn.v_proj.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.self_attn.v_proj.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.self_attn_layer_norm.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.29.self_attn_layer_norm.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.3.encoder_attn.k_proj.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.3.fc1.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.3.fc1.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.3.fc2.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.3.fc2.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.3.final_layer_norm.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.3.final_layer_norm.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.3.self_attn.k_proj.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.3.self_attn.k_proj.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.3.self_attn.out_proj.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.3.self_attn.out_proj.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.3.self_attn.q_proj.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.3.self_attn.q_proj.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.3.self_attn.v_proj.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.3.self_attn.v_proj.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.3.self_attn_layer_norm.bias": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.3.self_attn_layer_norm.weight": "model-00005-of-00027.safetensors",
    "decoder.model.decoder.layers.30.encoder_attn.k_proj.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.encoder_attn.k_proj.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.encoder_attn.out_proj.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.encoder_attn.out_proj.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.encoder_attn.q_proj.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.encoder_attn.q_proj.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.encoder_attn.v_proj.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.encoder_attn.v_proj.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.encoder_attn_layer_norm.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.encoder_attn_layer_norm.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.fc1.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.fc1.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.fc2.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.fc2.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.final_layer_norm.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.final_layer_norm.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.self_attn.k_proj.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.30.self_attn.k_proj.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.30.self_attn.out_proj.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.self_attn.out_proj.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.self_attn.q_proj.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.30.self_attn.q_proj.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.30.self_attn.v_proj.bias": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.30.self_attn.v_proj.weight": "model-00024-of-00027.safetensors",
    "decoder.model.decoder.layers.30.self_attn_layer_norm.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.30.self_attn_layer_norm.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.encoder_attn.k_proj.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.encoder_attn.k_proj.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.encoder_attn.out_proj.bias": "model-00027-of-00027.safetensors",
    "decoder.model.decoder.layers.31.encoder_attn.out_proj.weight": "model-00027-of-00027.safetensors",
    "decoder.model.decoder.layers.31.encoder_attn.q_proj.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.encoder_attn.q_proj.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.encoder_attn.v_proj.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.encoder_attn.v_proj.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.encoder_attn_layer_norm.bias": "model-00027-of-00027.safetensors",
    "decoder.model.decoder.layers.31.encoder_attn_layer_norm.weight": "model-00027-of-00027.safetensors",
    "decoder.model.decoder.layers.31.fc1.bias": "model-00027-of-00027.safetensors",
    "decoder.model.decoder.layers.31.fc1.weight": "model-00027-of-00027.safetensors",
    "decoder.model.decoder.layers.31.fc2.bias": "model-00027-of-00027.safetensors",
    "decoder.model.decoder.layers.31.fc2.weight": "model-00027-of-00027.safetensors",
    "decoder.model.decoder.layers.31.final_layer_norm.bias": "model-00027-of-00027.safetensors",
    "decoder.model.decoder.layers.31.final_layer_norm.weight": "model-00027-of-00027.safetensors",
    "decoder.model.decoder.layers.31.self_attn.k_proj.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.self_attn.k_proj.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.self_attn.out_proj.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.self_attn.out_proj.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.self_attn.q_proj.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.self_attn.q_proj.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.self_attn.v_proj.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.self_attn.v_proj.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.self_attn_layer_norm.bias": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.31.self_attn_layer_norm.weight": "model-00025-of-00027.safetensors",
    "decoder.model.decoder.layers.4.encoder_attn.k_proj.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.fc1.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.fc1.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.fc2.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.fc2.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.final_layer_norm.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.final_layer_norm.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.self_attn.k_proj.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.self_attn.k_proj.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.self_attn.out_proj.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.self_attn.out_proj.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.self_attn.q_proj.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.self_attn.q_proj.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.self_attn.v_proj.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.self_attn.v_proj.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.self_attn_layer_norm.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.4.self_attn_layer_norm.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.5.encoder_attn.k_proj.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.fc1.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.fc1.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.fc2.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.fc2.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.final_layer_norm.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.final_layer_norm.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.self_attn.k_proj.bias": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.5.self_attn.k_proj.weight": "model-00006-of-00027.safetensors",
    "decoder.model.decoder.layers.5.self_attn.out_proj.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.self_attn.out_proj.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.self_attn.q_proj.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.self_attn.q_proj.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.self_attn.v_proj.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.self_attn.v_proj.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.self_attn_layer_norm.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.5.self_attn_layer_norm.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.6.encoder_attn.k_proj.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.6.fc1.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.6.fc1.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.6.fc2.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.6.fc2.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.6.final_layer_norm.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.6.final_layer_norm.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.6.self_attn.k_proj.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.6.self_attn.k_proj.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.6.self_attn.out_proj.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.6.self_attn.out_proj.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.6.self_attn.q_proj.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.6.self_attn.q_proj.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.6.self_attn.v_proj.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.6.self_attn.v_proj.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.6.self_attn_layer_norm.bias": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.6.self_attn_layer_norm.weight": "model-00007-of-00027.safetensors",
    "decoder.model.decoder.layers.7.encoder_attn.k_proj.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.fc1.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.fc1.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.fc2.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.7.fc2.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.7.final_layer_norm.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.7.final_layer_norm.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.7.self_attn.k_proj.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.self_attn.k_proj.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.self_attn.out_proj.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.self_attn.out_proj.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.self_attn.q_proj.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.self_attn.q_proj.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.self_attn.v_proj.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.self_attn.v_proj.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.self_attn_layer_norm.bias": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.7.self_attn_layer_norm.weight": "model-00008-of-00027.safetensors",
    "decoder.model.decoder.layers.8.encoder_attn.k_proj.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.fc1.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.fc1.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.fc2.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.fc2.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.final_layer_norm.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.final_layer_norm.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.self_attn.k_proj.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.self_attn.k_proj.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.self_attn.out_proj.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.self_attn.out_proj.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.self_attn.q_proj.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.self_attn.q_proj.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.self_attn.v_proj.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.self_attn.v_proj.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.self_attn_layer_norm.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.8.self_attn_layer_norm.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.9.encoder_attn.k_proj.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.fc1.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.fc1.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.fc2.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.fc2.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.final_layer_norm.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.final_layer_norm.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.self_attn.k_proj.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.9.self_attn.k_proj.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.9.self_attn.out_proj.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.self_attn.out_proj.weight": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.self_attn.q_proj.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.9.self_attn.q_proj.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.9.self_attn.v_proj.bias": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.9.self_attn.v_proj.weight": "model-00009-of-00027.safetensors",
    "decoder.model.decoder.layers.9.self_attn_layer_norm.bias": "model-00010-of-00027.safetensors",
    "decoder.model.decoder.layers.9.self_attn_layer_norm.weight": "model-00010-of-00027.safetensors",
    "decoder.output_projection.weight": "model-00026-of-00027.safetensors",
    "enc_to_dec_proj.bias": "model-00027-of-00027.safetensors",
    "enc_to_dec_proj.weight": "model-00027-of-00027.safetensors",
    "encoder.embeddings.cls_token": "model-00003-of-00027.safetensors",
    "encoder.embeddings.patch_embeddings.projection.bias": "model-00003-of-00027.safetensors",
    "encoder.embeddings.patch_embeddings.projection.weight": "model-00003-of-00027.safetensors",
    "encoder.embeddings.position_embeddings": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.0.attention.attention.key.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.0.attention.attention.query.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.0.attention.attention.value.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.0.attention.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.0.attention.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.0.intermediate.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.0.intermediate.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.0.layernorm_after.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.0.layernorm_after.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.0.layernorm_before.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.0.layernorm_before.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.0.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.0.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.1.attention.attention.key.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.1.attention.attention.query.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.1.attention.attention.value.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.1.attention.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.1.attention.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.1.intermediate.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.1.intermediate.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.1.layernorm_after.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.1.layernorm_after.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.1.layernorm_before.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.1.layernorm_before.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.1.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.1.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.10.attention.attention.key.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.10.attention.attention.query.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.10.attention.attention.value.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.10.attention.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.10.attention.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.10.intermediate.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.10.intermediate.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.10.layernorm_after.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.10.layernorm_after.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.10.layernorm_before.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.10.layernorm_before.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.10.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.10.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.11.attention.attention.key.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.11.attention.attention.query.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.11.attention.attention.value.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.11.attention.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.11.attention.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.11.intermediate.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.11.intermediate.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.11.layernorm_after.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.11.layernorm_after.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.11.layernorm_before.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.11.layernorm_before.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.11.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.11.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.2.attention.attention.key.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.2.attention.attention.query.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.2.attention.attention.value.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.2.attention.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.2.attention.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.2.intermediate.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.2.intermediate.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.2.layernorm_after.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.2.layernorm_after.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.2.layernorm_before.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.2.layernorm_before.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.2.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.2.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.3.attention.attention.key.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.3.attention.attention.query.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.3.attention.attention.value.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.3.attention.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.3.attention.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.3.intermediate.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.3.intermediate.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.3.layernorm_after.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.3.layernorm_after.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.3.layernorm_before.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.3.layernorm_before.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.3.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.3.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.4.attention.attention.key.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.4.attention.attention.query.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.4.attention.attention.value.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.4.attention.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.4.attention.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.4.intermediate.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.4.intermediate.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.4.layernorm_after.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.4.layernorm_after.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.4.layernorm_before.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.4.layernorm_before.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.4.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.4.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.5.attention.attention.key.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.5.attention.attention.query.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.5.attention.attention.value.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.5.attention.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.5.attention.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.5.intermediate.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.5.intermediate.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.5.layernorm_after.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.5.layernorm_after.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.5.layernorm_before.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.5.layernorm_before.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.5.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.5.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.6.attention.attention.key.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.6.attention.attention.query.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.6.attention.attention.value.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.6.attention.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.6.attention.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.6.intermediate.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.6.intermediate.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.6.layernorm_after.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.6.layernorm_after.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.6.layernorm_before.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.6.layernorm_before.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.6.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.6.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.7.attention.attention.key.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.7.attention.attention.query.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.7.attention.attention.value.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.7.attention.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.7.attention.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.7.intermediate.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.7.intermediate.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.7.layernorm_after.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.7.layernorm_after.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.7.layernorm_before.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.7.layernorm_before.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.7.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.7.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.8.attention.attention.key.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.8.attention.attention.query.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.8.attention.attention.value.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.8.attention.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.8.attention.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.8.intermediate.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.8.intermediate.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.8.layernorm_after.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.8.layernorm_after.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.8.layernorm_before.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.8.layernorm_before.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.8.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.8.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.9.attention.attention.key.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.9.attention.attention.query.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.9.attention.attention.value.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.9.attention.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.9.attention.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.9.intermediate.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.9.intermediate.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.9.layernorm_after.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.9.layernorm_after.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.9.layernorm_before.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.9.layernorm_before.weight": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.9.output.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.encoder.layer.9.output.dense.weight": "model-00003-of-00027.safetensors",
    "encoder.layernorm.bias": "model-00003-of-00027.safetensors",
    "encoder.layernorm.weight": "model-00003-of-00027.safetensors",
    "encoder.pooler.dense.bias": "model-00003-of-00027.safetensors",
    "encoder.pooler.dense.weight": "model-00003-of-00027.safetensors"
  }
}