diff --git a/.gitattributes b/.gitattributes index bde9c8a80155c55155d56d16cb7e67a3273e0495..6cab3b21ef6abce6c488301bfd92a2259fcaf13c 100644 --- a/.gitattributes +++ b/.gitattributes @@ -122,3 +122,52 @@ checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.6 filter=lfs d checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_1.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_18.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_12.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text diff --git a/checkpoint_1007000/state.param_states.decoder.layers_17.pre_mlp_layer_norm.scale.v/.zarray b/checkpoint_1007000/state.param_states.decoder.layers_17.pre_mlp_layer_norm.scale.v/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..2d0ddea1f0046008cb8eb77c5f75d9445443f01b --- /dev/null +++ b/checkpoint_1007000/state.param_states.decoder.layers_17.pre_mlp_layer_norm.scale.v/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"