Commit
·
1153a1f
1
Parent(s):
2db1d34
Upload part 16
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +48 -0
- checkpoint_1007000/state.param_states.decoder.layers_2.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoint_1007000/state.param_states.decoder.layers_2.pre_cross_attention_layer_norm.scale.v/0 +0 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/.zarray.__tmp12014288596618633860.~1663960300089726~ +1 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/.zarray.__tmp12788005610953738983.~1663960299881865~ +1 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/.zarray.__tmp1752278582288188863.~1663960300384265~ +1 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/.zarray.__tmp3692844889417669524.~1663960300548388~ +1 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/.zarray.__tmp6398762328539168535.~1663960300013436~ +1 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/.zarray.__tmp6655180409517621627.~1663960299885095~ +1 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/.zarray.__tmp8086947124649123663.~1663960300133822~ +1 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.3 +3 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/.zarray.__tmp10051507613710607049.~1663960300090285~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/.zarray.__tmp11220523767467227228.~1663960300946012~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/.zarray.__tmp12391949257567665577.~1663960300134642~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/.zarray.__tmp15490448840588344018.~1663960300133322~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/.zarray.__tmp16767152659326521932.~1663960299927658~ +1 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/.zarray.__tmp11972489892599713968.~1663960300425646~ +1 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/.zarray.__tmp13226991599895094164.~1663960300825562~ +1 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/.zarray.__tmp15834185158498720343.~1663960300825448~ +1 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/.zarray.__tmp16172143578155850289.~1663960300727604~ +1 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/.zarray.__tmp3600075761690796327.~1663960300609255~ +1 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/.zarray.__tmp5714077514938043288.~1663960300504711~ +1 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/.zarray.__tmp7132194976859071764.~1663960300683980~ +1 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.3 +3 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_4.pre_mlp_layer_norm.scale/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_4.pre_mlp_layer_norm.scale/0 +0 -0
- checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/.zarray +1 -0
- checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/.zarray.__tmp16880061608743887200.~1663960300686090~ +1 -0
- checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/.zarray.__tmp17165400383502796712.~1663960300628136~ +1 -0
- checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/.zarray.__tmp2263231972689484636.~1663960300472320~ +1 -0
- checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/.zarray.__tmp5011423507129348440.~1663960301112996~ +1 -0
- checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/.zarray.__tmp5210789755887592551.~1663960300730092~ +1 -0
- checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/.zarray.__tmp7640900726591430468.~1663960300825801~ +1 -0
- checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/.zarray.__tmp8240428936776310696.~1663960300609870~ +1 -0
.gitattributes
CHANGED
@@ -803,3 +803,51 @@ checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/
|
|
803 |
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
804 |
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
805 |
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
803 |
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
804 |
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
805 |
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
806 |
+
checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
807 |
+
checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
808 |
+
checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
809 |
+
checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
810 |
+
checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
811 |
+
checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
812 |
+
checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
813 |
+
checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
814 |
+
checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
815 |
+
checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
816 |
+
checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
817 |
+
checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
818 |
+
checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
819 |
+
checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
820 |
+
checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
821 |
+
checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
822 |
+
checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
823 |
+
checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
824 |
+
checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
825 |
+
checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
826 |
+
checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
827 |
+
checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
828 |
+
checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
829 |
+
checkpoint_1007000/target.encoder.layers_6.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
830 |
+
checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
831 |
+
checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
832 |
+
checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
833 |
+
checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
834 |
+
checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
835 |
+
checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
836 |
+
checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
837 |
+
checkpoint_1007000/target.encoder.layers_3.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
838 |
+
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
839 |
+
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
840 |
+
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
841 |
+
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
842 |
+
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
843 |
+
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
844 |
+
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
845 |
+
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
846 |
+
checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
847 |
+
checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
848 |
+
checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
849 |
+
checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
850 |
+
checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
851 |
+
checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
852 |
+
checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
853 |
+
checkpoint_1007000/target.encoder.layers_2.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
checkpoint_1007000/state.param_states.decoder.layers_2.pre_cross_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_2.pre_cross_attention_layer_norm.scale.v/0
ADDED
Binary file (14.9 kB). View file
|
|
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.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_0.mlp.wi_0.kernel/.zarray.__tmp12014288596618633860.~1663960300089726~
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_0.mlp.wi_0.kernel/.zarray.__tmp12788005610953738983.~1663960299881865~
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_0.mlp.wi_0.kernel/.zarray.__tmp1752278582288188863.~1663960300384265~
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_0.mlp.wi_0.kernel/.zarray.__tmp3692844889417669524.~1663960300548388~
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_0.mlp.wi_0.kernel/.zarray.__tmp6398762328539168535.~1663960300013436~
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_0.mlp.wi_0.kernel/.zarray.__tmp6655180409517621627.~1663960299885095~
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_0.mlp.wi_0.kernel/.zarray.__tmp8086947124649123663.~1663960300133822~
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_0.mlp.wi_0.kernel/0.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ea4573d99b4cf9e92fa5a7759fb8e5fa5c49b22fa7b0aa9fee86cb2d5ef92d8
|
3 |
+
size 19513024
|
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acf3315487c37b31f13c43f7f0995e21d3e9809c95f93e53c6b4e5f8871a773b
|
3 |
+
size 19512192
|
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fee5e2f2d4e1c2503956f3ab9d46208f08d51bc871fc33b182ad4c1fe1819e0
|
3 |
+
size 19513578
|
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94c99f9b9c1d0c4f5771aeaee1a5b26c27d501b2be45368283645585cef8440e
|
3 |
+
size 19514039
|
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f616dc7f317549bdccddd80e92edc7b552a7b674ee55b614fcc711e50304f3a
|
3 |
+
size 19512753
|
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a4742829acdaaa34668cc4bb7cccd58fb630ada5f05b49ef3fef3b3490cf21e
|
3 |
+
size 19514188
|
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7538319e5935ef25993682778c6ab28918fd78f840ef7039ee40e8c6642785e6
|
3 |
+
size 19513611
|
checkpoint_1007000/target.decoder.layers_0.mlp.wi_0.kernel/0.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:570ccf817c95c094c440d6db4d865de00a68cc093ec570b70d35539008024604
|
3 |
+
size 19513296
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.out.kernel/.zarray.__tmp10051507613710607049.~1663960300090285~
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_1.encoder_decoder_attention.out.kernel/.zarray.__tmp11220523767467227228.~1663960300946012~
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_1.encoder_decoder_attention.out.kernel/.zarray.__tmp12391949257567665577.~1663960300134642~
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_1.encoder_decoder_attention.out.kernel/.zarray.__tmp15490448840588344018.~1663960300133322~
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_1.encoder_decoder_attention.out.kernel/.zarray.__tmp16767152659326521932.~1663960299927658~
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_15.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_15.self_attention.key.kernel/.zarray.__tmp11972489892599713968.~1663960300425646~
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_15.self_attention.key.kernel/.zarray.__tmp13226991599895094164.~1663960300825562~
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_15.self_attention.key.kernel/.zarray.__tmp15834185158498720343.~1663960300825448~
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_15.self_attention.key.kernel/.zarray.__tmp16172143578155850289.~1663960300727604~
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_15.self_attention.key.kernel/.zarray.__tmp3600075761690796327.~1663960300609255~
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_15.self_attention.key.kernel/.zarray.__tmp5714077514938043288.~1663960300504711~
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_15.self_attention.key.kernel/.zarray.__tmp7132194976859071764.~1663960300683980~
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_15.self_attention.key.kernel/0.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cc0f95007a56ff1eb8ba0097a9879018c87d0f4e3504f0d0039886dcd76ffbd
|
3 |
+
size 7819509
|
checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13aae3f59e400741685bf041da2daea6a85b9579a4c34a02555e8985e959ddbf
|
3 |
+
size 7823058
|
checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cfc1bbd7b8f1a6df9b23b535d9e727fb6ec408e8c4a3079d4856d29944afbd2
|
3 |
+
size 7819803
|
checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71100aa37ac0635005a32739ffb4c2fe2b4810c2d35435a20c428cb15d8a5401
|
3 |
+
size 7822563
|
checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e2c8ce6727c28644df0c028dde23891789959b9a1567c4ffc6f831352662d34
|
3 |
+
size 7827575
|
checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36b285b98b066176df58676f520fb52ad16bbdeed8d0b042b3c0802b77769a84
|
3 |
+
size 7823625
|
checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fae25077759bef2dc7bbc5ba24a969f7a33f0e419475728328b79e1e8a9e7d63
|
3 |
+
size 7818571
|
checkpoint_1007000/target.decoder.layers_15.self_attention.key.kernel/0.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb53bb5f579caedabbcb632f8c10b7069d3d7a3fa044a20a1dc0972e276f6887
|
3 |
+
size 7831476
|
checkpoint_1007000/target.decoder.layers_4.pre_mlp_layer_norm.scale/.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/target.decoder.layers_4.pre_mlp_layer_norm.scale/0
ADDED
Binary file (15 kB). View file
|
|
checkpoint_1007000/target.encoder.layers_15.attention.out.kernel/.zarray
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.encoder.layers_15.attention.out.kernel/.zarray.__tmp16880061608743887200.~1663960300686090~
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.encoder.layers_15.attention.out.kernel/.zarray.__tmp17165400383502796712.~1663960300628136~
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.encoder.layers_15.attention.out.kernel/.zarray.__tmp2263231972689484636.~1663960300472320~
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.encoder.layers_15.attention.out.kernel/.zarray.__tmp5011423507129348440.~1663960301112996~
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.encoder.layers_15.attention.out.kernel/.zarray.__tmp5210789755887592551.~1663960300730092~
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.encoder.layers_15.attention.out.kernel/.zarray.__tmp7640900726591430468.~1663960300825801~
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.encoder.layers_15.attention.out.kernel/.zarray.__tmp8240428936776310696.~1663960300609870~
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}
|