{ "metadata": { "total_size": 13046378496 }, "weight_map": { "_base_encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin", "_base_encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_decoder.embed_tokens.weight": "pytorch_model-00002-of-00002.bin", "_decoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_lm_head.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder._underlying_model.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder._underlying_model.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.0.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.0.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.1.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.1.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.2.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.2.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.3.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.3.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.4.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.4.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.embed_tokens.weight": "pytorch_model-00002-of-00002.bin", "_sled_encoder.sled_base_model_prefix.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin", "_underlying_model.decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.decoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.lm_head.weight": "pytorch_model-00001-of-00002.bin", "_underlying_model.shared.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.decoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.lm_head.weight": "pytorch_model-00001-of-00002.bin", "sled_base_model_prefix.shared.weight": "pytorch_model-00001-of-00002.bin" } }