| *.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 |
|
|