pytorch_model.bin.index.json

{
  "metadata": {
    "total_size": 22919639040
  },
  "weight_map": {
    "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00003.bin",
    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
    "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
    "decoder.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
    "decoder.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
    "encoder.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
    "mm_projector.0.bias": "pytorch_model-00003-of-00003.bin",
    "mm_projector.0.weight": "pytorch_model-00003-of-00003.bin",
    "mm_projector.2.bias": "pytorch_model-00003-of-00003.bin",
    "mm_projector.2.weight": "pytorch_model-00003-of-00003.bin",
    "shared.weight": "pytorch_model-00001-of-00003.bin",
    "vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00003-of-00003.bin",
    "vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00003-of-00003.bin"
  }
}