diff --git a/.gitattributes b/.gitattributes index 959ef622dcf7c92f017c38c030bb409983a1fdcf..c13a7e218ca95f80111376a75028609a74a5bb82 100644 --- a/.gitattributes +++ b/.gitattributes @@ -271,3 +271,54 @@ checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.value.kern 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 diff --git a/checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.value.kernel/.zarray b/checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.value.kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..ddb67420063a3a02f5bd9b9eb19e636151970a4c --- /dev/null +++ b/checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.value.kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"