diff --git a/.gitattributes b/.gitattributes index 0168020dd6bdb6936f40558ccf17fd2ad5bd40eb..8d1f5b4b9943658656f5860d43f81200ca3616c2 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1494,3 +1494,54 @@ checkpoint_1007000/target.decoder.layers_2.self_attention.key.kernel/0.4 filter= 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 diff --git a/checkpoint_1007000/target.decoder.layers_0.self_attention.query.kernel/.zarray b/checkpoint_1007000/target.decoder.layers_0.self_attention.query.kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..ddb67420063a3a02f5bd9b9eb19e636151970a4c --- /dev/null +++ b/checkpoint_1007000/target.decoder.layers_0.self_attention.query.kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"