diff --git a/.gitattributes b/.gitattributes index 64b439ce1c5163b5e3e8bc59b0247a9498450907..373001f577aaa1a43fa674fba28c0576bcb0ba10 100644 --- a/.gitattributes +++ b/.gitattributes @@ -3101,3 +3101,48 @@ checkpoint_1007000/target.decoder.layers_1.mlp.wi_1.kernel/0.2 filter=lfs diff=l 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 diff --git a/checkpoint_1007000/state.param_states.decoder.layers_11.pre_self_attention_layer_norm.scale.v/.zarray b/checkpoint_1007000/state.param_states.decoder.layers_11.pre_self_attention_layer_norm.scale.v/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..2d0ddea1f0046008cb8eb77c5f75d9445443f01b --- /dev/null +++ b/checkpoint_1007000/state.param_states.decoder.layers_11.pre_self_attention_layer_norm.scale.v/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"