Commit
·
53c8883
1
Parent(s):
80d4197
Upload part 56
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +45 -0
- checkpoint_1007000/state.param_states.decoder.layers_6.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoint_1007000/state.param_states.decoder.layers_6.pre_self_attention_layer_norm.scale.v/0 +0 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray.__tmp10096213465051516093.~1663960300729750~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray.__tmp1437121107918676566.~1663960300728672~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray.__tmp16815428771206975186.~1663960300891281~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray.__tmp3829264275660445046.~1663960300467538~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray.__tmp4399171417319396480.~1663960300683459~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray.__tmp8622904520302365342.~1663960300602647~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray.__tmp96472989138992427.~1663960300622365~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.3 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/.zarray.__tmp15392526484812228073.~1663960300467159~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/.zarray.__tmp16081514963271822487.~1663960300824193~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/.zarray.__tmp16165803137518944016.~1663960300465834~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/.zarray.__tmp16477529522571669260.~1663960300609917~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/.zarray.__tmp17345275530017372204.~1663960300552709~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/.zarray.__tmp5997230937773945770.~1663960300687190~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/.zarray.__tmp13036696574977996125.~1663960300872822~ +1 -0
- checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/.zarray.__tmp13338217960105046591.~1663960300685536~ +1 -0
- checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/.zarray.__tmp1381500123483220693.~1663960300778501~ +1 -0
- checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/.zarray.__tmp914870319506369220.~1663960300492026~ +1 -0
- checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray.__tmp14567836385690951514.~1663960301071770~ +1 -0
- checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray.__tmp15595714208269458883.~1663960300554132~ +1 -0
- checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray.__tmp18405479603212386933.~1663960300601688~ +1 -0
- checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray.__tmp3711466519506984829.~1663960300728487~ +1 -0
- checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray.__tmp4106614488589665798.~1663960300547801~ +1 -0
- checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray.__tmp5956538183775927452.~1663960300420505~ +1 -0
- checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray.__tmp7062544252647458405.~1663960300775727~ +1 -0
- checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.3 +3 -0
- checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.6 +3 -0
.gitattributes
CHANGED
|
@@ -2827,3 +2827,48 @@ checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/
|
|
| 2827 |
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
| 2828 |
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2829 |
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2827 |
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
| 2828 |
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2829 |
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
| 2830 |
+
checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 2831 |
+
checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 2832 |
+
checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2833 |
+
checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 2834 |
+
checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 2835 |
+
checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 2836 |
+
checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 2837 |
+
checkpoint_1007000/target.encoder.layers_9.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 2838 |
+
checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 2839 |
+
checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 2840 |
+
checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2841 |
+
checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 2842 |
+
checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 2843 |
+
checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 2844 |
+
checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 2845 |
+
checkpoint_1007000/target.decoder.layers_8.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 2846 |
+
checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
| 2847 |
+
checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 2848 |
+
checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 2849 |
+
checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2850 |
+
checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
| 2851 |
+
checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
| 2852 |
+
checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2853 |
+
checkpoint_1007000/target.encoder.layers_0.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
| 2854 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 2855 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 2856 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2857 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 2858 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 2859 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 2860 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 2861 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 2862 |
+
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 2863 |
+
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 2864 |
+
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2865 |
+
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 2866 |
+
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 2867 |
+
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 2868 |
+
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 2869 |
+
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 2870 |
+
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 2871 |
+
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 2872 |
+
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2873 |
+
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 2874 |
+
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
checkpoint_1007000/state.param_states.decoder.layers_6.pre_self_attention_layer_norm.scale.v/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}
|
checkpoint_1007000/state.param_states.decoder.layers_6.pre_self_attention_layer_norm.scale.v/0
ADDED
|
Binary file (15.1 kB). View file
|
|
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray.__tmp10096213465051516093.~1663960300729750~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray.__tmp1437121107918676566.~1663960300728672~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray.__tmp16815428771206975186.~1663960300891281~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray.__tmp3829264275660445046.~1663960300467538~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray.__tmp4399171417319396480.~1663960300683459~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray.__tmp8622904520302365342.~1663960300602647~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/.zarray.__tmp96472989138992427.~1663960300622365~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6ad50e4a709b6fa3cfa28e3a4c6808d6c69aa509fe4dafcedbc17a29c294dfc
|
| 3 |
+
size 7820760
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1844c28756dd1c9be2eb52c563c38e326dd9f7abed397e3217d70fc639cd5e0
|
| 3 |
+
size 7833858
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62e639f44d7db5cdb2633d87f3a745802041dd75f353c5ab97ba7e200ed72421
|
| 3 |
+
size 7832883
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cee3c1f254e5b037139bf967eb513582a38d2b62f0d5230796e167fc2165e05
|
| 3 |
+
size 7819355
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:614ec7c3b0af3836b1d253e967f64579ed25b9ba23c1b2932b2ac874f28ce8b5
|
| 3 |
+
size 7833577
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33b52f02b515badc59215537d08809e053506060a2244754e3369f9bc9d621f4
|
| 3 |
+
size 7818785
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bcbb5111fc0309b0bb78a8a70b96d71c5c82f2bd9bf88378676f7d08465f14e
|
| 3 |
+
size 7824547
|
checkpoint_1007000/target.decoder.layers_12.self_attention.key.kernel/0.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d639f507c852483e7912f6ebacd9f4b706c291b7b442bfa913e6277715114280
|
| 3 |
+
size 7820208
|
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/.zarray.__tmp15392526484812228073.~1663960300467159~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/.zarray.__tmp16081514963271822487.~1663960300824193~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/.zarray.__tmp16165803137518944016.~1663960300465834~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/.zarray.__tmp16477529522571669260.~1663960300609917~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/.zarray.__tmp17345275530017372204.~1663960300552709~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/.zarray.__tmp5997230937773945770.~1663960300687190~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08378401d04670087e69d7a6c97f93e072f93396cabbf269ce2b5271d27d3aa5
|
| 3 |
+
size 7812863
|
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:842f249b7e0b8e82f0cfc8258a9d80df507c8170ce106fa2530d43f8297d6981
|
| 3 |
+
size 7842271
|
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bc8616f17046f45b428a253261a15aaf6bd46d92343844157a61d845d30076b
|
| 3 |
+
size 7828532
|
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0917c1afef82631c5559d64e3217a073eac05b192b2fb5ee1be521ed3e8b0770
|
| 3 |
+
size 7848636
|
checkpoint_1007000/target.decoder.layers_16.self_attention.value.kernel/0.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92d7deaa3a324a76697bde6d7df085bf4a444467909f840fb345c4a27dcfde97
|
| 3 |
+
size 7843871
|
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/.zarray.__tmp13036696574977996125.~1663960300872822~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[512,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/.zarray.__tmp13338217960105046591.~1663960300685536~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[512,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/.zarray.__tmp1381500123483220693.~1663960300778501~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[512,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.out.kernel/.zarray.__tmp914870319506369220.~1663960300492026~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[512,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray.__tmp14567836385690951514.~1663960301071770~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray.__tmp15595714208269458883.~1663960300554132~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray.__tmp18405479603212386933.~1663960300601688~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray.__tmp3711466519506984829.~1663960300728487~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray.__tmp4106614488589665798.~1663960300547801~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray.__tmp5956538183775927452.~1663960300420505~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/.zarray.__tmp7062544252647458405.~1663960300775727~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f6f25e93ecaf3326c4734a9b133324bc574888ec3e2e5f57b1132fb7734604b
|
| 3 |
+
size 19517667
|
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:715e73fd6dadf38d6cb96418127eeb5e265ff96f24530ea5398af972cd26940d
|
| 3 |
+
size 19518209
|
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1aa5dfdccee2b6dee6024be5a51b4a779975509ee43c83ba26cbf71ec4d6854
|
| 3 |
+
size 19516661
|
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32f8e241e8198a155eb91721f40bbc5eaff68c52e1d6cb019e628591a500e2b1
|
| 3 |
+
size 19518356
|
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9f5afc63413f491598f7c2263598cae09fb03f1f5b85a0f999dd5caa3a568b7
|
| 3 |
+
size 19516943
|
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2f442f0c99b43dc513bf824dc4d2e97d8644a5e6537aaeea589249499033381
|
| 3 |
+
size 19517752
|
checkpoint_1007000/target.decoder.layers_22.mlp.wi_1.kernel/0.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87d5d2def2e3dd48e8ad810fb339de6e23f65c4c39e4f37b0061398952dfc9d7
|
| 3 |
+
size 19517065
|