Commit
·
563417d
1
Parent(s):
d67cac2
Upload part 9
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +46 -0
- checkpoint_1007000/state.param_states.encoder.layers_14.pre_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoint_1007000/state.param_states.encoder.layers_14.pre_attention_layer_norm.scale.v/0 +0 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/.zarray.__tmp10698029373918293210.~1663960299960302~ +1 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/.zarray.__tmp2811847496614678480.~1663960300550723~ +1 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/.zarray.__tmp3904973126971017634.~1663960300089714~ +1 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/.zarray.__tmp4756890692258687341.~1663960299834049~ +1 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/.zarray.__tmp48440933064589369.~1663960300015330~ +1 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/.zarray.__tmp6994713304716703807.~1663960301029136~ +1 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/.zarray.__tmp9275528857631177208.~1663960300133715~ +1 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.3 +3 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/.zarray.__tmp10684706001739984359.~1663960300465565~ +1 -0
- checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/.zarray.__tmp10895474852075995219.~1663960300549710~ +1 -0
- checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/.zarray.__tmp1135743413873390284.~1663960300312232~ +1 -0
- checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/.zarray.__tmp16077642490987012457.~1663960300385403~ +1 -0
- checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/.zarray.__tmp1832998805999099116.~1663960300497063~ +1 -0
- checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/.zarray.__tmp18435040581273713004.~1663960300686535~ +1 -0
- checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.3 +3 -0
- checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_8.pre_cross_attention_layer_norm.scale/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_8.pre_cross_attention_layer_norm.scale/0 +0 -0
- checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/.zarray.__tmp1840379829062282856.~1663960300937034~ +1 -0
- checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/.zarray.__tmp792607635482850572.~1663960300865179~ +1 -0
- checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.4 +3 -0
- checkpoint_1007000/target.encoder.layers_15.pre_mlp_layer_norm.scale/.zarray +1 -0
- checkpoint_1007000/target.encoder.layers_15.pre_mlp_layer_norm.scale/0 +0 -0
- checkpoint_1007000/target.encoder.layers_2.pre_attention_layer_norm.scale/.zarray +1 -0
- checkpoint_1007000/target.encoder.layers_2.pre_attention_layer_norm.scale/0 +0 -0
- checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/.zarray +1 -0
- checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/.zarray.__tmp10201642036656898085.~1663960300468378~ +1 -0
- checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/.zarray.__tmp1040037177903247305.~1663960300983875~ +1 -0
- checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/.zarray.__tmp12358517478981963293.~1663960300777191~ +1 -0
- checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/.zarray.__tmp1281093732280486016.~1663960300725065~ +1 -0
- checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/.zarray.__tmp14817733808080836238.~1663960300551929~ +1 -0
.gitattributes
CHANGED
|
@@ -457,3 +457,49 @@ checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.0 filter=
|
|
| 457 |
checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 458 |
checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 459 |
checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 457 |
checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 458 |
checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 459 |
checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 460 |
+
checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 461 |
+
checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 462 |
+
checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 463 |
+
checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 464 |
+
checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 465 |
+
checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 466 |
+
checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 467 |
+
checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 468 |
+
checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 469 |
+
checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 470 |
+
checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 471 |
+
checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 472 |
+
checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 473 |
+
checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 474 |
+
checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 475 |
+
checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 476 |
+
checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 477 |
+
checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 478 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
| 479 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 480 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 481 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 482 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
| 483 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
| 484 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 485 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
| 486 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 487 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 488 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 489 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 490 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 491 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 492 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 493 |
+
checkpoint_1007000/target.encoder.layers_5.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 494 |
+
checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
| 495 |
+
checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 496 |
+
checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 497 |
+
checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 498 |
+
checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
| 499 |
+
checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
| 500 |
+
checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 501 |
+
checkpoint_1007000/target.encoder.layers_21.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
| 502 |
+
checkpoint_1007000/target.encoder.layers_23.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 503 |
+
checkpoint_1007000/target.encoder.layers_23.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 504 |
+
checkpoint_1007000/target.encoder.layers_23.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 505 |
+
checkpoint_1007000/target.encoder.layers_23.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
checkpoint_1007000/state.param_states.encoder.layers_14.pre_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.encoder.layers_14.pre_attention_layer_norm.scale.v/0
ADDED
|
Binary file (15.2 kB). View file
|
|
|
checkpoint_1007000/target.decoder.layers_0.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_0.self_attention.key.kernel/.zarray.__tmp10698029373918293210.~1663960299960302~
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_0.self_attention.key.kernel/.zarray.__tmp2811847496614678480.~1663960300550723~
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_0.self_attention.key.kernel/.zarray.__tmp3904973126971017634.~1663960300089714~
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_0.self_attention.key.kernel/.zarray.__tmp4756890692258687341.~1663960299834049~
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_0.self_attention.key.kernel/.zarray.__tmp48440933064589369.~1663960300015330~
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_0.self_attention.key.kernel/.zarray.__tmp6994713304716703807.~1663960301029136~
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_0.self_attention.key.kernel/.zarray.__tmp9275528857631177208.~1663960300133715~
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_0.self_attention.key.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37f6286826b052c469463d5af2840be81b37392ab9503ae67da559fc9b6cd932
|
| 3 |
+
size 7806149
|
checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6b40a38bfffab4c271aa769cc248204ed1f104ae773d8f490f1d643daac2624
|
| 3 |
+
size 7814265
|
checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65fefd316ada6404927f25130adf7d66f78e6a31c92b9d0ea8fd768018b2e365
|
| 3 |
+
size 7811420
|
checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25cf300a39e919ca6b289aacc33c773f36c0575309cfb04339af5e921c78e542
|
| 3 |
+
size 7809228
|
checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2124730455d2960a98c2f23fe42cd7f200ca8a837ed1467dea558d32bf0de302
|
| 3 |
+
size 7810201
|
checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4926449e8865131b1d10b61b2eb8dc003a7308ed7fa79e1a7509b8c970973b6a
|
| 3 |
+
size 7810738
|
checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44ad48cd6e002966a289865dcd0251e32d811a0ffa567b9e6ed3e7fc0cc2751d
|
| 3 |
+
size 7809710
|
checkpoint_1007000/target.decoder.layers_0.self_attention.key.kernel/0.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78a05329b68bfc586ed405550fda3fe95068f541c665f4b31d28eb4c2c5690c4
|
| 3 |
+
size 7810640
|
checkpoint_1007000/target.decoder.layers_19.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_19.self_attention.key.kernel/.zarray.__tmp10684706001739984359.~1663960300465565~
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_19.self_attention.key.kernel/.zarray.__tmp10895474852075995219.~1663960300549710~
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_19.self_attention.key.kernel/.zarray.__tmp1135743413873390284.~1663960300312232~
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_19.self_attention.key.kernel/.zarray.__tmp16077642490987012457.~1663960300385403~
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_19.self_attention.key.kernel/.zarray.__tmp1832998805999099116.~1663960300497063~
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_19.self_attention.key.kernel/.zarray.__tmp18435040581273713004.~1663960300686535~
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_19.self_attention.key.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:618881df0b45e7e7ce38c2c345ebbf067b2051af30dbf10c09d06d41802a2a66
|
| 3 |
+
size 7816737
|
checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1aa42e6f6873528c26975b829e6d22c5b3e3a74d3869725121d13982ddc9eb88
|
| 3 |
+
size 7825334
|
checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7c22bdae94330c98d88f49395ea48acc9e037c62bd96eb3151009656f2429d6
|
| 3 |
+
size 7812976
|
checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12c98a61096abc2c16b3c69ce4303e60f8aad38033971ca9951a1a80d01ab7e9
|
| 3 |
+
size 7816634
|
checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:496bc6086d6558c09f4cccec1657c823715aa4642c2e32a7b5d14db8c8cf4c4c
|
| 3 |
+
size 7815044
|
checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cec73ce3c703fed120f3241499d6dd07ba67af103487ab90b326374cb5fcb6e
|
| 3 |
+
size 7812501
|
checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23818a3d7334f6e9e0283118b7569c9d1db247d5097f309e6ffb29f5e4352e7e
|
| 3 |
+
size 7824443
|
checkpoint_1007000/target.decoder.layers_19.self_attention.key.kernel/0.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:245058c3c4ff95f8a5a952b36927b082e38cc5b2c8ce98172b7d4fec55c9efd6
|
| 3 |
+
size 7815502
|
checkpoint_1007000/target.decoder.layers_8.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_8.pre_cross_attention_layer_norm.scale/0
ADDED
|
Binary file (15 kB). View file
|
|
|
checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/.zarray.__tmp1840379829062282856.~1663960300937034~
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_8.self_attention.key.kernel/.zarray.__tmp792607635482850572.~1663960300865179~
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_8.self_attention.key.kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d151396928cd2998d05fe043a75700f27cf383ef138c9108bc6cf26e0d35289
|
| 3 |
+
size 7826819
|
checkpoint_1007000/target.decoder.layers_8.self_attention.key.kernel/0.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaf3662194eb4544de28b15042fa67309247fd669d4ce516c9c78a21cd705725
|
| 3 |
+
size 7828246
|
checkpoint_1007000/target.encoder.layers_15.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.encoder.layers_15.pre_mlp_layer_norm.scale/0
ADDED
|
Binary file (14.7 kB). View file
|
|
|
checkpoint_1007000/target.encoder.layers_2.pre_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.encoder.layers_2.pre_attention_layer_norm.scale/0
ADDED
|
Binary file (15.1 kB). View file
|
|
|
checkpoint_1007000/target.encoder.layers_21.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.encoder.layers_21.mlp.wo.kernel/.zarray.__tmp10201642036656898085.~1663960300468378~
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.encoder.layers_21.mlp.wo.kernel/.zarray.__tmp1040037177903247305.~1663960300983875~
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.encoder.layers_21.mlp.wo.kernel/.zarray.__tmp12358517478981963293.~1663960300777191~
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.encoder.layers_21.mlp.wo.kernel/.zarray.__tmp1281093732280486016.~1663960300725065~
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.encoder.layers_21.mlp.wo.kernel/.zarray.__tmp14817733808080836238.~1663960300551929~
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}
|