diff --git a/.gitattributes b/.gitattributes index b89f6c50a76861f47b8e120630cf75063eedbd13..4e898678400a8a45791d03b9a4e0fb8eba98aba8 100644 --- a/.gitattributes +++ b/.gitattributes @@ -358,3 +358,206 @@ checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.mlp.wi_1.kernel/0.0 f checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +savedmodels/musiccoca_mv212f_cpu_compat/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text +checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text diff --git a/checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_0.pre_mlp_layer_norm.scale.v/.zarray b/checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_0.pre_mlp_layer_norm.scale.v/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..fb266c57e8e0dee6193b582ba985adeb7c50f8cf --- /dev/null +++ b/checkpoints/llm_large_x3047_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_0.pre_mlp_layer_norm.scale.v/.zarray @@ -0,0 +1 @@ +{"chunks":[1024],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"