diff --git a/.gitattributes b/.gitattributes index 8d1f5b4b9943658656f5860d43f81200ca3616c2..5619ecc0a0fcd31d555af5b62789d7064e0b8ee2 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1545,3 +1545,49 @@ checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/3.0 filter=lfs diff=lf 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 +checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text diff --git a/checkpoint_1007000/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/.zarray b/checkpoint_1007000/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..2d0ddea1f0046008cb8eb77c5f75d9445443f01b --- /dev/null +++ b/checkpoint_1007000/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"