diff --git a/.gitattributes b/.gitattributes index 64309a5c526798acbd61f8377cb9eac67d1cdc3e..959ef622dcf7c92f017c38c030bb409983a1fdcf 100644 --- a/.gitattributes +++ b/.gitattributes @@ -224,3 +224,50 @@ checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel 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 diff --git a/checkpoint_1007000/state.param_states.encoder.layers_16.pre_mlp_layer_norm.scale.v/.zarray b/checkpoint_1007000/state.param_states.encoder.layers_16.pre_mlp_layer_norm.scale.v/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..2d0ddea1f0046008cb8eb77c5f75d9445443f01b --- /dev/null +++ b/checkpoint_1007000/state.param_states.encoder.layers_16.pre_mlp_layer_norm.scale.v/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"