diff --git "a/pytorch_model.bin.index.json" "b/pytorch_model.bin.index.json" --- "a/pytorch_model.bin.index.json" +++ "b/pytorch_model.bin.index.json" @@ -3,564 +3,565 @@ "total_size": 14970478592 }, "weight_map": { - "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin", - "decoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin", - "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", - "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin", - "lm_head.weight": "pytorch_model-00002-of-00002.bin", - "shared.weight": "pytorch_model-00001-of-00002.bin" + "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin", + "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin", + "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin", + "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00002-of-00003.bin", + "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin", + "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin", + "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin", + "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin", + "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin", + "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin", + "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-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-00003-of-00003.bin", + "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin", + "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00003-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-00003-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-00002-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-00002-of-00003.bin", + "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-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-00002-of-00003.bin", + "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin", + "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-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-00002-of-00003.bin", + "lm_head.weight": "pytorch_model-00003-of-00003.bin", + "shared.weight": "pytorch_model-00001-of-00003.bin" } }