Commit
·
db684dd
1
Parent(s):
d689be8
Upload part 30
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.decoder.layers_13.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoint_1007000/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/.zarray.__tmp12409322873689395006.~1663960300089849~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/.zarray.__tmp14551936232511702523.~1663960300227664~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/.zarray.__tmp15597877627935176396.~1663960300017616~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/1.0 +3 -0
- checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/2.0 +3 -0
- checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/3.0 +3 -0
- checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/4.0 +3 -0
- checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/5.0 +3 -0
- checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/6.0 +3 -0
- checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/7.0 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/.zarray.__tmp17545959101359184009.~1663960300602053~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/.zarray.__tmp17856109268251686970.~1663960300271650~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/.zarray.__tmp227164167752699561.~1663960300626655~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/.zarray.__tmp4731854672731091164.~1663960300990257~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/.zarray.__tmp9904602313415314703.~1663960300423092~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/.zarray.__tmp10124636526798063471.~1663960300774964~ +1 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/.zarray.__tmp13225873251825425754.~1663960300501475~ +1 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/.zarray.__tmp15530978618470535287.~1663960300623654~ +1 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/.zarray.__tmp17129643380383773551.~1663960300176619~ +1 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/.zarray.__tmp17630076616503346697.~1663960300547135~ +1 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/.zarray.__tmp9185647636123386636.~1663960300776662~ +1 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/.zarray.__tmp9901379260848895590.~1663960300936745~ +1 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.3 +3 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_22.pre_self_attention_layer_norm.scale/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_22.pre_self_attention_layer_norm.scale/0 +0 -0
- checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/.zarray.__tmp12494912640791181416.~1663960300936785~ +1 -0
- checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/.zarray.__tmp14168177597997916633.~1663960300609125~ +1 -0
- checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/.zarray.__tmp16559268995570192847.~1663960300689042~ +1 -0
- checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/.zarray.__tmp17827712019379812001.~1663960300601692~ +1 -0
- checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/.zarray.__tmp3163465050790104906.~1663960300505087~ +1 -0
- checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/.zarray.__tmp5219696822044432968.~1663960300387308~ +1 -0
.gitattributes
CHANGED
@@ -1545,3 +1545,49 @@ checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/3.0 filter=lfs diff=lf
|
|
1545 |
checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
1546 |
checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
1547 |
checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1545 |
checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
1546 |
checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
1547 |
checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
1548 |
+
checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
1549 |
+
checkpoint_1007000/target.encoder.layers_13.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
1550 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
1551 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
1552 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
1553 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
1554 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
1555 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
1556 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
1557 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
1558 |
+
checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
1559 |
+
checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
1560 |
+
checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
1561 |
+
checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
1562 |
+
checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
1563 |
+
checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
1564 |
+
checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
1565 |
+
checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
1566 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
1567 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
1568 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
1569 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
1570 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
1571 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
1572 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
1573 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
1574 |
+
checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
1575 |
+
checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
1576 |
+
checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
1577 |
+
checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
1578 |
+
checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
1579 |
+
checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
1580 |
+
checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
1581 |
+
checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
1582 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
1583 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
1584 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
1585 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
1586 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
1587 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
1588 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
1589 |
+
checkpoint_1007000/target.encoder.layers_6.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
1590 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
1591 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
1592 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
1593 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
checkpoint_1007000/state.param_states.decoder.layers_13.pre_mlp_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_13.pre_mlp_layer_norm.scale.v/0
ADDED
Binary file (14.9 kB). View file
|
|
checkpoint_1007000/target.decoder.layers_1.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_1.self_attention.out.kernel/.zarray.__tmp12409322873689395006.~1663960300089849~
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.self_attention.out.kernel/.zarray.__tmp14551936232511702523.~1663960300227664~
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.self_attention.out.kernel/.zarray.__tmp15597877627935176396.~1663960300017616~
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.self_attention.out.kernel/0.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33529afe3003a420dda3693ac8f53eb86a961294e8e40d30d7d973b1434bd28f
|
3 |
+
size 7817343
|
checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/1.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:875eb68f34db0dc8f226c24603985e31ba7d1c48389e773d19a66d6227c3d83c
|
3 |
+
size 7816652
|
checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/2.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:455c95d11a84b51a5f7a31d5462984bb08fa68c9e855e3bc8fa0468dfdaa952a
|
3 |
+
size 7812795
|
checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/3.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ccc90c7f3e28a656f75049e0682fd63bb9898a1010ecdfacd108589159be2c6
|
3 |
+
size 7818192
|
checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/4.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aafe9492f35b9888fd10a2cff555b8a51be28b14ae59999f34a1996264339936
|
3 |
+
size 7817940
|
checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/5.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6b8d898e2c05bee47db8a4bd158e3facef28f7a039e8c8f0bce459cc3196059
|
3 |
+
size 7814379
|
checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/6.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85bbcb374a5da7046e3d9c5ff4cab3c9e459a402ef2577de6c78a64fc0ea5a6d
|
3 |
+
size 7820210
|
checkpoint_1007000/target.decoder.layers_1.self_attention.out.kernel/7.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8749cbdb83a1fc1e5ed985ba27bdc59b9766587531c29c583908b3db28836908
|
3 |
+
size 7817160
|
checkpoint_1007000/target.decoder.layers_12.self_attention.query.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.query.kernel/.zarray.__tmp17545959101359184009.~1663960300602053~
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.query.kernel/.zarray.__tmp17856109268251686970.~1663960300271650~
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.query.kernel/.zarray.__tmp227164167752699561.~1663960300626655~
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.query.kernel/.zarray.__tmp4731854672731091164.~1663960300990257~
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.query.kernel/.zarray.__tmp9904602313415314703.~1663960300423092~
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.query.kernel/0.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f43366965b456ee8d48e7d78ec56c12bea13568657f7a7d42b08b5c0c7df84b
|
3 |
+
size 7806929
|
checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67223b271d63450d229d82eb08143ea7a1de6c3d10722dc5a40f99b11ff21b95
|
3 |
+
size 7816167
|
checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebd7f3e3377d70edadeb554fd27cb2a3f57a1c6cc9e85cf1cbf20543cd20813f
|
3 |
+
size 7813559
|
checkpoint_1007000/target.decoder.layers_12.self_attention.query.kernel/0.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef142978d9f719b7e48ed8afede3107e22f241e18dc340725ede6d68b62aa19f
|
3 |
+
size 7805069
|
checkpoint_1007000/target.decoder.layers_21.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_21.mlp.wi_0.kernel/.zarray.__tmp10124636526798063471.~1663960300774964~
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_21.mlp.wi_0.kernel/.zarray.__tmp13225873251825425754.~1663960300501475~
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_21.mlp.wi_0.kernel/.zarray.__tmp15530978618470535287.~1663960300623654~
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_21.mlp.wi_0.kernel/.zarray.__tmp17129643380383773551.~1663960300176619~
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_21.mlp.wi_0.kernel/.zarray.__tmp17630076616503346697.~1663960300547135~
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_21.mlp.wi_0.kernel/.zarray.__tmp9185647636123386636.~1663960300776662~
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_21.mlp.wi_0.kernel/.zarray.__tmp9901379260848895590.~1663960300936745~
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_21.mlp.wi_0.kernel/0.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a8c70fdbea45633190907845a33021b915120edf5184da6a606b1c22cd07ed5
|
3 |
+
size 19527216
|
checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1648c953dfe1b15b7244f611aa0174e1cbb69c2aa7afa7cb1b93eb77d7a02f0a
|
3 |
+
size 19525101
|
checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ec06e4b27d0e1f2f141103fb3b8fa9fd2cb9cfb0fa287a7be72814c743167e5
|
3 |
+
size 19525930
|
checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5854cf1d28f586475a9e419d80120c66ddb943333088f1979b9cbb141a572215
|
3 |
+
size 19527782
|
checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba7c4f58d9f72d9406c71b0962a72beb700dc488e5c85d3e0941f7aaa7cdf735
|
3 |
+
size 19524981
|
checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0057974591370851e743ea276f76fb5d11d22e3a19ea3298ee5b75a803367189
|
3 |
+
size 19525724
|
checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef2c8b25e12ee350b8953b755ee00edc533cab039cbe3a15a3ce0ff670f0a07e
|
3 |
+
size 19526596
|
checkpoint_1007000/target.decoder.layers_21.mlp.wi_0.kernel/0.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4049e747a9263a0b9df596a8d3d5caf24e2da37d40f3184d69a2148fbed1d528
|
3 |
+
size 19528816
|
checkpoint_1007000/target.decoder.layers_22.pre_self_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_22.pre_self_attention_layer_norm.scale/0
ADDED
Binary file (14 kB). View file
|
|
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.query.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_4.encoder_decoder_attention.query.kernel/.zarray.__tmp12494912640791181416.~1663960300936785~
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_4.encoder_decoder_attention.query.kernel/.zarray.__tmp14168177597997916633.~1663960300609125~
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_4.encoder_decoder_attention.query.kernel/.zarray.__tmp16559268995570192847.~1663960300689042~
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_4.encoder_decoder_attention.query.kernel/.zarray.__tmp17827712019379812001.~1663960300601692~
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_4.encoder_decoder_attention.query.kernel/.zarray.__tmp3163465050790104906.~1663960300505087~
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_4.encoder_decoder_attention.query.kernel/.zarray.__tmp5219696822044432968.~1663960300387308~
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}
|