Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +250 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_self_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_2.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_2.pre_self_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_3.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_3.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_0.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_0.pre_cross_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_12.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_12.pre_self_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_13.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_13.pre_cross_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_4.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_4.pre_cross_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_6.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_6.pre_self_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.relpos_bias.rel_embedding.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.relpos_bias.rel_embedding.v/0.0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.encoder.layers_11.pre_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.encoder.layers_11.pre_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.encoder.layers_5.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.encoder.layers_5.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.key.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.value.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.out.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.out.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.out.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.value.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.out.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.value.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.query.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.key.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.pre_cross_attention_layer_norm.scale/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.pre_cross_attention_layer_norm.scale/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wi_0.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_0.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_1.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.pre_cross_attention_layer_norm.scale/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.pre_cross_attention_layer_norm.scale/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.query.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.out.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.query.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.value.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wi_1.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.query.kernel/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_19.pre_self_attention_layer_norm.scale/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_19.pre_self_attention_layer_norm.scale/0 +0 -0
.gitattributes
CHANGED
@@ -561,3 +561,253 @@ checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layer
|
|
561 |
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
|
562 |
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
|
563 |
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
561 |
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
|
562 |
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
|
563 |
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
|
564 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
565 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
566 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
567 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
568 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
569 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
570 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
571 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
572 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
573 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
574 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
575 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
576 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
577 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
578 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
579 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
580 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
581 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
582 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
583 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
584 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
585 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
586 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
587 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
588 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
589 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
590 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
591 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
592 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
593 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
594 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
595 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
596 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
597 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
598 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
599 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
600 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
601 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
602 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
603 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
604 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
605 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
606 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
607 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
608 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
609 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
610 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
611 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
612 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
613 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
614 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
615 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
616 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
617 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
618 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
619 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
620 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
621 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
622 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
623 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
624 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
625 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
626 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
627 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
628 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
629 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
630 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
631 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
632 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
633 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
634 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
635 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
636 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
637 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
638 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
639 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
640 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
641 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
642 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
643 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
644 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
645 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
646 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
647 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
648 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
649 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
650 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
651 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
652 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
653 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
654 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
655 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
656 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
657 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
658 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
659 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
660 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
661 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
662 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
663 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
664 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
665 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
666 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
667 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
668 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
669 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
670 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
671 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
672 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
673 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
674 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
675 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
676 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
677 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
678 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
679 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
680 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
681 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
682 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
683 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
684 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
685 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
686 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
687 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
688 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
689 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
690 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
691 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
692 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
693 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
694 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
695 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
696 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
697 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_19.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
698 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
699 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
700 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
701 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
702 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
703 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
704 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
705 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
706 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
707 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
708 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
709 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
710 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
711 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
712 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_6.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
713 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
714 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
715 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
716 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
717 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_2.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
718 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
719 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
720 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
721 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
722 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
723 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
724 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
725 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
726 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
727 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
728 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
729 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
730 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_13.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
731 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
732 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
733 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
734 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
735 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
736 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
737 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_6.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
738 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
739 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
740 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
741 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
742 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
743 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
744 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
745 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_5.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
746 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_5.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
747 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
748 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
749 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
750 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
751 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
752 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
753 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
754 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_0.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
755 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
756 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
757 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
758 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
759 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
760 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
761 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
762 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
763 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
764 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_8.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
765 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
766 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
767 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
768 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
769 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
770 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_11.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
771 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.logits_dense.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
772 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.logits_dense.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
773 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
774 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
775 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_20.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
776 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
777 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
778 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
779 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_5.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
780 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_5.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
781 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
782 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_5.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
783 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
784 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_10.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
785 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
786 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
787 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_7.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
788 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
789 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
790 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
791 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_1.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
792 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_3.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
793 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
794 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
795 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_18.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
796 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_21.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
797 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
798 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
799 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
800 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
801 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_10.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
802 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
803 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
804 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
805 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_5.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
806 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
807 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_9.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
808 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
809 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
810 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
811 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
812 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
813 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_mlp_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_mlp_layer_norm.scale.v/0
ADDED
Binary file (2.78 kB). View file
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_self_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_1.pre_self_attention_layer_norm.scale.v/0
ADDED
Binary file (2.75 kB). View file
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_2.pre_self_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_2.pre_self_attention_layer_norm.scale.v/0
ADDED
Binary file (2.73 kB). View file
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_3.pre_mlp_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_3.pre_mlp_layer_norm.scale.v/0
ADDED
Binary file (2.78 kB). View file
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_0.pre_cross_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_0.pre_cross_attention_layer_norm.scale.v/0
ADDED
Binary file (2.93 kB). View file
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_12.pre_self_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_12.pre_self_attention_layer_norm.scale.v/0
ADDED
Binary file (2.84 kB). View file
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_13.pre_cross_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_13.pre_cross_attention_layer_norm.scale.v/0
ADDED
Binary file (2.79 kB). View file
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_4.pre_cross_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_4.pre_cross_attention_layer_norm.scale.v/0
ADDED
Binary file (2.87 kB). View file
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_6.pre_self_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_6.pre_self_attention_layer_norm.scale.v/0
ADDED
Binary file (2.89 kB). View file
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.relpos_bias.rel_embedding.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[12,128],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[12,128],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.relpos_bias.rel_embedding.v/0.0
ADDED
Binary file (2.32 kB). View file
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.encoder.layers_11.pre_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/state.param_states.encoder.layers_11.pre_attention_layer_norm.scale.v/0
ADDED
Binary file (2.81 kB). View file
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.encoder.layers_5.pre_mlp_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/state.param_states.encoder.layers_5.pre_mlp_layer_norm.scale.v/0
ADDED
Binary file (2.84 kB). View file
|
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.key.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.value.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.out.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.out.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.out.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.value.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.out.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.value.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.query.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.key.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.pre_cross_attention_layer_norm.scale/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.pre_cross_attention_layer_norm.scale/0
ADDED
Binary file (2.81 kB). View file
|
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wi_0.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,2048],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,2048],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_0.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,2048],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,2048],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_1.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,2048],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,2048],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.pre_cross_attention_layer_norm.scale/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.pre_cross_attention_layer_norm.scale/0
ADDED
Binary file (2.76 kB). View file
|
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.query.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.out.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.query.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.value.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wi_1.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,2048],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,2048],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.query.kernel/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768,768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768,768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_19.pre_self_attention_layer_norm.scale/.zarray
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_19.pre_self_attention_layer_norm.scale/0
ADDED
Binary file (2.68 kB). View file
|
|