Commit
·
6d3453f
1
Parent(s):
f2038ac
Upload part 14
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +53 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/.zarray.__tmp10728549375677064994.~1663960300090404~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/.zarray.__tmp11236523353068830748.~1663960300074679~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/.zarray.__tmp11633998362442887536.~1663960300016846~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/.zarray.__tmp11818502354139142660.~1663960300347593~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/.zarray.__tmp12582392156644863207.~1663960300548853~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/.zarray.__tmp3118436071326852120.~1663960300133376~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/.zarray.__tmp8890225177344953236.~1663960299883385~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.3 +3 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_10.pre_cross_attention_layer_norm.scale/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_10.pre_cross_attention_layer_norm.scale/0 +0 -0
- checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/.zarray.__tmp10864704857316665397.~1663960300272115~ +1 -0
- checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/.zarray.__tmp8179432841680863540.~1663960300467714~ +1 -0
- checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.3 +3 -0
- checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/.zarray.__tmp12621064089923553944.~1663960300471110~ +1 -0
- checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/.zarray.__tmp920986222252901076.~1663960300425287~ +1 -0
- checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/1.0 +3 -0
- checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/2.0 +3 -0
- checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/3.0 +3 -0
- checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/4.0 +3 -0
- checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/5.0 +3 -0
- checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/6.0 +3 -0
- checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/7.0 +3 -0
- checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/.zarray.__tmp1199691337994657358.~1663960300425096~ +1 -0
- checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/.zarray.__tmp13104808374533942291.~1663960300552207~ +1 -0
- checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/.zarray.__tmp15738084505425695318.~1663960300500517~ +1 -0
- checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/.zarray.__tmp2562574817749316267.~1663960301112753~ +1 -0
- checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/.zarray.__tmp6082463700529864267.~1663960300385908~ +1 -0
- checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/.zarray.__tmp6605423927687461219.~1663960300888480~ +1 -0
- checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/.zarray.__tmp8997445159364145736.~1663960300725997~ +1 -0
- checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/0.0 +3 -0
.gitattributes
CHANGED
|
@@ -703,3 +703,56 @@ checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/6.0 filter=lfs diff=lf
|
|
| 703 |
checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 704 |
checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 705 |
checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 703 |
checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 704 |
checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 705 |
checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 706 |
+
checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
| 707 |
+
checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
| 708 |
+
checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 709 |
+
checkpoint_1007000/target.encoder.layers_23.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
| 710 |
+
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
| 711 |
+
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 712 |
+
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 713 |
+
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 714 |
+
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
| 715 |
+
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
| 716 |
+
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 717 |
+
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
| 718 |
+
checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 719 |
+
checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 720 |
+
checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 721 |
+
checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 722 |
+
checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 723 |
+
checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 724 |
+
checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 725 |
+
checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 726 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 727 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 728 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 729 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 730 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 731 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 732 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 733 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 734 |
+
checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 735 |
+
checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 736 |
+
checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 737 |
+
checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 738 |
+
checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 739 |
+
checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 740 |
+
checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 741 |
+
checkpoint_1007000/target.encoder.layers_14.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 742 |
+
checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
| 743 |
+
checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 744 |
+
checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 745 |
+
checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 746 |
+
checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
| 747 |
+
checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
| 748 |
+
checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 749 |
+
checkpoint_1007000/target.encoder.layers_21.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
| 750 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
| 751 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 752 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 753 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 754 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
| 755 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
| 756 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 757 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
| 758 |
+
checkpoint_1007000/target.encoder.layers_10.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_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_1.encoder_decoder_attention.value.kernel/.zarray.__tmp10728549375677064994.~1663960300090404~
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_1.encoder_decoder_attention.value.kernel/.zarray.__tmp11236523353068830748.~1663960300074679~
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_1.encoder_decoder_attention.value.kernel/.zarray.__tmp11633998362442887536.~1663960300016846~
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_1.encoder_decoder_attention.value.kernel/.zarray.__tmp11818502354139142660.~1663960300347593~
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_1.encoder_decoder_attention.value.kernel/.zarray.__tmp12582392156644863207.~1663960300548853~
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_1.encoder_decoder_attention.value.kernel/.zarray.__tmp3118436071326852120.~1663960300133376~
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_1.encoder_decoder_attention.value.kernel/.zarray.__tmp8890225177344953236.~1663960299883385~
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_1.encoder_decoder_attention.value.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:297379575586955734376f5bc10aaabdbfda6ca3245ff9b7f1c31bebc759c2db
|
| 3 |
+
size 7816409
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71da8e750449313911a10a6d577a04e9d7fbfe1e101501ec59a551a478901d72
|
| 3 |
+
size 7818082
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f89518dc569518530b7855bfbbdad3e94c8efbc121c472a3819fbbcbb6ab1fd
|
| 3 |
+
size 7819358
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f84608d77911fb5bf1efb5bf6294c9c75d5ab97070d608dde88cc29a4a492fb1
|
| 3 |
+
size 7817069
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd983610e2a9dc5cfdad23cc1953bb67ab0628f52f993ffe6e66821298038f92
|
| 3 |
+
size 7817809
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78417795537f753bc0e80e503937246aa484abb076e5bcabbed30320d0febef9
|
| 3 |
+
size 7818889
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a097ddfe173c54a348dde68c8680154105d2d470e7b81714a6291c014d91c0f1
|
| 3 |
+
size 7816908
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.value.kernel/0.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a14774c045ad158e9c567860ba6d99fbdb9b8b29f9e4a8d7412327405fcbca6
|
| 3 |
+
size 7815183
|
checkpoint_1007000/target.decoder.layers_10.pre_cross_attention_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_10.pre_cross_attention_layer_norm.scale/0
ADDED
|
Binary file (14.9 kB). View file
|
|
|
checkpoint_1007000/target.decoder.layers_13.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_13.self_attention.value.kernel/.zarray.__tmp10864704857316665397.~1663960300272115~
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_13.self_attention.value.kernel/.zarray.__tmp8179432841680863540.~1663960300467714~
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_13.self_attention.value.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0e784fedb645f24ab18ca0a0c5ca16e4993663afe2636ef8e25b8dc3df2f93e
|
| 3 |
+
size 7830664
|
checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4acea03ce0ec6ef123e2bffb902b1eb43f2ef08441ff48581baef6a35e9f0822
|
| 3 |
+
size 7860204
|
checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb835a6848ce95c1a889d88c06f7970e209a25b0b7ea953bf29b8e0a0d8b5d09
|
| 3 |
+
size 7831919
|
checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c7dd8c73d0ade71940e97b8c962a234a5b863b0bc056ba4bf170ac1a19de534
|
| 3 |
+
size 7823233
|
checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19202861706ab3ddf457c4423b7bb0e8752e5d34962b87f204da832960a83567
|
| 3 |
+
size 7838981
|
checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b58c9b868bd903efdc871311000f83a4958e1f50e2bb0568bb92b448ee44cbfe
|
| 3 |
+
size 7835539
|
checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bb7823da7724b80d50c0c618ae3793ae1c350009e2f2080f862a7e7f785dcef
|
| 3 |
+
size 7843373
|
checkpoint_1007000/target.decoder.layers_13.self_attention.value.kernel/0.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07a49e24a2240cc2cb3e46ad91f9ac985298fa72d28e8a108539b09d48707f09
|
| 3 |
+
size 7824183
|
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[1280,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[10240,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/.zarray.__tmp12621064089923553944.~1663960300471110~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[1280,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[10240,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/.zarray.__tmp920986222252901076.~1663960300425287~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[1280,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[10240,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6fa7921dfc50d1e3566adfd3ad3b2f63ae7678eb2acc505b84fb2d560a35d67
|
| 3 |
+
size 19542147
|
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:add625de692fa25c88dfc6f1a9db9cdc267943236f97c3710549176e5258e0fb
|
| 3 |
+
size 19542127
|
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c50060538bfc665a5c4500557235b8e94cc9f672907e0070530a97871b2b4a87
|
| 3 |
+
size 19541114
|
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dcdf192b5a8cc8d507fcaa14dca0fabe35c5d98b8842df7857c6e2b3fe8a7f9
|
| 3 |
+
size 19542946
|
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/4.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc027ccf558402e658cf3bb90fab687f0a778b596681917bdb514f29d8cb272d
|
| 3 |
+
size 19542658
|
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/5.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9ea5a04c30f05add18f39e9bf2132836499ba8188efc15dc9d8a30b97599644
|
| 3 |
+
size 19541974
|
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/6.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c74196fa40552ee9fab2c331df7331cebaf6bc30df824058ea3caf128413c301
|
| 3 |
+
size 19542915
|
checkpoint_1007000/target.decoder.layers_5.mlp.wo.kernel/7.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b1b696acf662eba05fd4d7c885f9dc15beec8aa2a8414d3b5ab3e8f393b2477
|
| 3 |
+
size 19541821
|
checkpoint_1007000/target.decoder.layers_6.self_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.decoder.layers_6.self_attention.out.kernel/.zarray.__tmp1199691337994657358.~1663960300425096~
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_6.self_attention.out.kernel/.zarray.__tmp13104808374533942291.~1663960300552207~
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_6.self_attention.out.kernel/.zarray.__tmp15738084505425695318.~1663960300500517~
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_6.self_attention.out.kernel/.zarray.__tmp2562574817749316267.~1663960301112753~
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_6.self_attention.out.kernel/.zarray.__tmp6082463700529864267.~1663960300385908~
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_6.self_attention.out.kernel/.zarray.__tmp6605423927687461219.~1663960300888480~
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_6.self_attention.out.kernel/.zarray.__tmp8997445159364145736.~1663960300725997~
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_6.self_attention.out.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc12161aa2a88583579268470f1cc8bcfb37c7031343f4dc0323645fea71a04e
|
| 3 |
+
size 7815623
|