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 +373 -0
- checkpoints/llm_base_x4286_c1860k/checkpoint +3 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_0.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_0.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_0.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_0.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_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_2.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_3.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_3.pre_self_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.relpos_bias_depth.rel_embedding.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.relpos_bias_depth.rel_embedding.v/0.0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_0.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_0.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_0.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_0.pre_self_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_1.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_1.pre_cross_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_1.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_1.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_1.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_1.pre_self_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_10.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_10.pre_cross_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_10.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_10.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_10.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_10.pre_self_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_11.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_11.pre_cross_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_11.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_11.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_11.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_11.pre_self_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_12.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_12.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_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_12.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_13.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_13.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_13.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_13.pre_self_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_14.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_14.pre_cross_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_14.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_14.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_14.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_14.pre_self_attention_layer_norm.scale.v/0 +0 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_15.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_15.pre_cross_attention_layer_norm.scale.v/0 +0 -0
.gitattributes
CHANGED
|
@@ -811,3 +811,376 @@ checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.depth_decoder.depth_la
|
|
| 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
| 814 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_0.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 815 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 816 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 817 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 818 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 819 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 820 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 821 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 822 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_5.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 823 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 824 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_14.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 825 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_7.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 826 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_3.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 827 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 828 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_17.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 829 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 830 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 831 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 832 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_16.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 833 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 834 |
+
checkpoints/llm_large_x3047_c1860k/target.token_embedder.embedding/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 835 |
+
checkpoints/llm_large_x3047_c1860k/target.token_embedder.embedding/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 836 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 837 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 838 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 839 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 840 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 841 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_12.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 842 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_11.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 843 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_13.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 844 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_2.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 845 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 846 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 847 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 848 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_15.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 849 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 850 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 851 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 852 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_14.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 853 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_17.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 854 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 855 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 856 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 857 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 858 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 859 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_4.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 860 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 861 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 862 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_18.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 863 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 864 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 865 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_8.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 866 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 867 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_1.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 868 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_16.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 869 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 870 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 871 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 872 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 873 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 874 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_22.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 875 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_9.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 876 |
+
checkpoints/llm_large_x3047_c1860k/target.decoder.decoder.temporal_decoder.layers_4.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 877 |
+
checkpoints/llm_base_x4286_c1860k/checkpoint filter=lfs diff=lfs merge=lfs -text
|
| 878 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 879 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 880 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 881 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 882 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 883 |
+
checkpoints/llm_large_x3047_c1860k/target.encoder.layers_23.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 884 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_2.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 885 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_8.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 886 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 887 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 888 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 889 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 890 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 891 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_6.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 892 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 893 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 894 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 895 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 896 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_8.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 897 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_4.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 898 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 899 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_8.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 900 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_9.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 901 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 902 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 903 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_3.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 904 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_8.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 905 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 906 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_7.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 907 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_8.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 908 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 909 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 910 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_9.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 911 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_8.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 912 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 913 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 914 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 915 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_4.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 916 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 917 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_11.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 918 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 919 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 920 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 921 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 922 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 923 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_9.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 924 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_7.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 925 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_6.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 926 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 927 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_10.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 928 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 929 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 930 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 931 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_3.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 932 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_10.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 933 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_8.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 934 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_3.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 935 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 936 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_9.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 937 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 938 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_6.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 939 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_7.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 940 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 941 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_4.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 942 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_11.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 943 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_13.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 944 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_1.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 945 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_9.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 946 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 947 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_8.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 948 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 949 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_4.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 950 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 951 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_19.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 952 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_7.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 953 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_13.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 954 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 955 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 956 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 957 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_10.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 958 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_5.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 959 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_13.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 960 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 961 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 962 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_5.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 963 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 964 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_11.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 965 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 966 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 967 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_3.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 968 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_9.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 969 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 970 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 971 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 972 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_4.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 973 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_5.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 974 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_9.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 975 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_10.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 976 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_17.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 977 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 978 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_2.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 979 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_13.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 980 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_2.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 981 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_5.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 982 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_9.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 983 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 984 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_16.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 985 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_7.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 986 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_6.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 987 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_4.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 988 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_6.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 989 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 990 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_16.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 991 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_3.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 992 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_14.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 993 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_16.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 994 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_6.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 995 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_2.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 996 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_6.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 997 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_18.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 998 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 999 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1000 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_3.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1001 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_4.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1002 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_1.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1003 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1004 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_1.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1005 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1006 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1007 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_10.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1008 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1009 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_6.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1010 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_0.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1011 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_9.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1012 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_2.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1013 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1014 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_6.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1015 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_16.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1016 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_2.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1017 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_11.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1018 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_5.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1019 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_7.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1020 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_17.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1021 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1022 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1023 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_10.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1024 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1025 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1026 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1027 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_7.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1028 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_14.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1029 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1030 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1031 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_2.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1032 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_17.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1033 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1034 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_16.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1035 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_3.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1036 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1037 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1038 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1039 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_13.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1040 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_7.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1041 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_6.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1042 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_10.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1043 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_10.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1044 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1045 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_0.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1046 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_2.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1047 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_1.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1048 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_5.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1049 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_4.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1050 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_10.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1051 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1052 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_11.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1053 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_4.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1054 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_4.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1055 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_10.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1056 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_11.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1057 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_18.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1058 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_6.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1059 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1060 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1061 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1062 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_16.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1063 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_5.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1064 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_7.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1065 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1066 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_13.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1067 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1068 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_7.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1069 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_5.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1070 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_9.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1071 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_7.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1072 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1073 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_10.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1074 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_7.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1075 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1076 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1077 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1078 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_1.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1079 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1080 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1081 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1082 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1083 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1084 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1085 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_7.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1086 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_8.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1087 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_19.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1088 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1089 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_4.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1090 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_5.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1091 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_8.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1092 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_19.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1093 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1094 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1095 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_9.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1096 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1097 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_9.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1098 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_8.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1099 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_6.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1100 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_8.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1101 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_0.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1102 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_1.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1103 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_0.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1104 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_4.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1105 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_0.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1106 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_0.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1107 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_8.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1108 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1109 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_13.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1110 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_11.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1111 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1112 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_18.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1113 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_8.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1114 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_7.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1115 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_0.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1116 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_9.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1117 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_18.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1118 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_9.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1119 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_4.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1120 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_7.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1121 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_3.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1122 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1123 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1124 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1125 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_19.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1126 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_1.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1127 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1128 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_18.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1129 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_11.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1130 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_2.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1131 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_11.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1132 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_10.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1133 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1134 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_4.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1135 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1136 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_8.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1137 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1138 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_2.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1139 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1140 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_0.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1141 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_3.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1142 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_7.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1143 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_0.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1144 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_12.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1145 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_5.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1146 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_3.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1147 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_14.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1148 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_11.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1149 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_18.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1150 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_10.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1151 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_5.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1152 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_17.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1153 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_2.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1154 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_6.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1155 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1156 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1157 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_4.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1158 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_11.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1159 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_14.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1160 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_4.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1161 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_13.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1162 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_9.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1163 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_6.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1164 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_5.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1165 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_19.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1166 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_8.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1167 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1168 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_15.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1169 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_11.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1170 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1171 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_0.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1172 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_5.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1173 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_1.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1174 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.logits_dense.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1175 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.logits_dense.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1176 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_8.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1177 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_3.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1178 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_5.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1179 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_10.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1180 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_0.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1181 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_7.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1182 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_11.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1183 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_3.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1184 |
+
checkpoints/llm_base_x4286_c1860k/target.encoder.layers_8.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1185 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.temporal_decoder.layers_1.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1186 |
+
checkpoints/llm_base_x4286_c1860k/target.decoder.decoder.depth_decoder.depth_layers_2.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
checkpoints/llm_base_x4286_c1860k/checkpoint
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a772893769281208fbba5e6c75279ebe1afbed20f86620927e9bd04713d67fe5
|
| 3 |
+
size 2995665
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_0.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_0.pre_mlp_layer_norm.scale.v/0
ADDED
|
Binary file (2.76 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_0.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_0.pre_self_attention_layer_norm.scale.v/0
ADDED
|
Binary file (2.8 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_2.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_2.pre_mlp_layer_norm.scale.v/0
ADDED
|
Binary file (2.71 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.depth_layers_3.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_3.pre_self_attention_layer_norm.scale.v/0
ADDED
|
Binary file (2.72 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.relpos_bias_depth.rel_embedding.v/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[12,16],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[12,16],"zarr_format":2}
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.depth_decoder.relpos_bias_depth.rel_embedding.v/0.0
ADDED
|
Binary file (776 Bytes). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_0.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.temporal_decoder.layers_0.pre_mlp_layer_norm.scale.v/0
ADDED
|
Binary file (2.92 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_0.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_0.pre_self_attention_layer_norm.scale.v/0
ADDED
|
Binary file (2.82 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_1.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_1.pre_cross_attention_layer_norm.scale.v/0
ADDED
|
Binary file (2.91 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.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.temporal_decoder.layers_1.pre_mlp_layer_norm.scale.v/0
ADDED
|
Binary file (2.9 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.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.temporal_decoder.layers_1.pre_self_attention_layer_norm.scale.v/0
ADDED
|
Binary file (2.9 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_10.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_10.pre_cross_attention_layer_norm.scale.v/0
ADDED
|
Binary file (2.85 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_10.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.temporal_decoder.layers_10.pre_mlp_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_10.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_10.pre_self_attention_layer_norm.scale.v/0
ADDED
|
Binary file (2.86 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_11.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_11.pre_cross_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_11.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.temporal_decoder.layers_11.pre_mlp_layer_norm.scale.v/0
ADDED
|
Binary file (2.83 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_11.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_11.pre_self_attention_layer_norm.scale.v/0
ADDED
|
Binary file (2.86 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_12.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_12.pre_cross_attention_layer_norm.scale.v/0
ADDED
|
Binary file (2.83 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_12.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.temporal_decoder.layers_12.pre_mlp_layer_norm.scale.v/0
ADDED
|
Binary file (2.83 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_13.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.temporal_decoder.layers_13.pre_mlp_layer_norm.scale.v/0
ADDED
|
Binary file (2.82 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_13.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_13.pre_self_attention_layer_norm.scale.v/0
ADDED
|
Binary file (2.81 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_14.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_14.pre_cross_attention_layer_norm.scale.v/0
ADDED
|
Binary file (2.82 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_14.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.temporal_decoder.layers_14.pre_mlp_layer_norm.scale.v/0
ADDED
|
Binary file (2.8 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_14.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_14.pre_self_attention_layer_norm.scale.v/0
ADDED
|
Binary file (2.8 kB). View file
|
|
|
checkpoints/llm_base_x4286_c1860k/state.param_states.decoder.decoder.temporal_decoder.layers_15.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_15.pre_cross_attention_layer_norm.scale.v/0
ADDED
|
Binary file (2.82 kB). View file
|
|
|