*.7z filter=lfs diff=lfs merge=lfs -text *.arrow filter=lfs diff=lfs merge=lfs -text *.bin filter=lfs diff=lfs merge=lfs -text *.bz2 filter=lfs diff=lfs merge=lfs -text *.ftz filter=lfs diff=lfs merge=lfs -text *.gz filter=lfs diff=lfs merge=lfs -text *.h5 filter=lfs diff=lfs merge=lfs -text *.joblib filter=lfs diff=lfs merge=lfs -text *.lfs.* filter=lfs diff=lfs merge=lfs -text *.mlmodel filter=lfs diff=lfs merge=lfs -text *.model filter=lfs diff=lfs merge=lfs -text *.msgpack filter=lfs diff=lfs merge=lfs -text *.npy filter=lfs diff=lfs merge=lfs -text *.npz filter=lfs diff=lfs merge=lfs -text *.onnx filter=lfs diff=lfs merge=lfs -text *.ot filter=lfs diff=lfs merge=lfs -text *.parquet filter=lfs diff=lfs merge=lfs -text *.pb filter=lfs diff=lfs merge=lfs -text *.pickle filter=lfs diff=lfs merge=lfs -text *.pkl filter=lfs diff=lfs merge=lfs -text *.pt filter=lfs diff=lfs merge=lfs -text *.pth filter=lfs diff=lfs merge=lfs -text *.rar filter=lfs diff=lfs merge=lfs -text saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.tar.* filter=lfs diff=lfs merge=lfs -text *.tflite filter=lfs diff=lfs merge=lfs -text *.tgz filter=lfs diff=lfs merge=lfs -text *.wasm filter=lfs diff=lfs merge=lfs -text *.xz filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/train_ds-003-of-004.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/train_ds-001-of-004.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/checkpoint filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/train_ds-000-of-004.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/train_ds-002-of-004.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/15.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/9.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/21.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/12.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/61.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/22.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/28.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/31.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/14.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/37.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/59.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/27.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/56.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/40.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/24.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/60.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/43.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/47.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/32.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/33.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/35.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/8.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/38.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/54.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/20.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/50.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/30.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/29.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/11.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/58.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/41.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/36.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/44.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/46.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/51.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/17.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/57.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/25.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/23.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/55.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/45.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/13.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/62.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/63.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/19.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/48.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/52.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/49.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/53.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/39.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/16.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/18.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/26.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/42.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/10.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.token_embedder.embedding/34.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.61 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.39 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.36 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.17 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.43 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.9 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.49 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.37 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.47 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.56 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.8 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.41 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.58 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.29 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.54 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.50 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.32 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.55 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.11 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.52 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.40 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.45 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.23 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.59 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.31 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.46 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.10 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.57 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.38 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.16 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.14 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.15 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.30 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.28 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.60 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.51 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.26 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.19 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.22 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.35 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.25 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.48 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.20 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.18 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.34 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.62 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.44 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.12 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.42 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.24 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.63 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.27 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.33 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.21 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.53 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.logits_dense.kernel/0.13 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_10.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_12.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_13.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_10.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_22.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_23.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_1.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_23.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_7.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_17.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_11.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_11.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_9.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_17.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_14.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_21.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_14.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_19.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_18.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_4.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_20.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_0.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_19.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_3.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_16.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_1.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_13.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_21.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_8.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_18.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_5.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.key.kernel/.zarray.__tmp17580245886536144534.~1663960300070201~ filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.query.kernel/.zarray.__tmp17600714105111994306.~1663960300776623~ filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.query.kernel/.zarray.__tmp13223404566358898156.~1663960300501056~ filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.query.kernel/.zarray filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.query.kernel/.zarray.__tmp18395897283964991681.~1663960300685953~ filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.key.kernel/.zarray filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.key.kernel/.zarray.__tmp686775373109079395.~1663960300545752~ filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_22.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.query.kernel/.zarray.__tmp12721826995102804480.~1663960300822091~ filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.query.kernel/.zarray.__tmp8858887114860817705.~1663960300383726~ filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.query.kernel/.zarray.__tmp8976497894109748696.~1663960300502842~ filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text