diff --git a/.gitattributes b/.gitattributes index fe44fb98f686c4477912a8036bc44ea7d89964ac..e65789909d4e323306c446dca18424af867e1ef9 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1990,3 +1990,52 @@ checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/4.0 filter=lfs diff=lfs checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_2.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_8.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_2.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_8.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_2.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_2.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_2.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_2.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text diff --git a/checkpoint_1007000/state.param_states.decoder.layers_23.pre_self_attention_layer_norm.scale.v/.zarray b/checkpoint_1007000/state.param_states.decoder.layers_23.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_23.pre_self_attention_layer_norm.scale.v/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"