Commit
·
4f1fdb7
1
Parent(s):
9460453
Upload part 26
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.encoder.layers_13.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoint_1007000/state.param_states.encoder.layers_13.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoint_1007000/target.decoder.layers_15.pre_mlp_layer_norm.scale/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_15.pre_mlp_layer_norm.scale/0 +0 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/.zarray.__tmp14026161881874612929.~1663960300423164~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/.zarray.__tmp14669013644749652312.~1663960300822625~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/.zarray.__tmp18190767523125055035.~1663960300683840~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/.zarray.__tmp4157870226440063089.~1663960300631997~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/.zarray.__tmp557031704751848400.~1663960300468619~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/.zarray.__tmp7489622347298658804.~1663960300313373~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/.zarray.__tmp7961904283916720111.~1663960300549206~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/1.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/2.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/3.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/4.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/5.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/6.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/7.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/.zarray.__tmp10299372109499927135.~1663960300549158~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/.zarray.__tmp11634642641137155406.~1663960300386224~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/.zarray.__tmp12783591421484397450.~1663960300422099~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/.zarray.__tmp14543171622674484344.~1663960300467496~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/.zarray.__tmp17111790465239777774.~1663960300549615~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/.zarray.__tmp6562102490701697533.~1663960300632000~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/.zarray.__tmp7354295375789531146.~1663960300775471~ +1 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/1.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/2.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/3.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/4.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/5.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/6.0 +3 -0
- checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/7.0 +3 -0
- checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/.zarray.__tmp10484147404724947140.~1663960300308272~ +1 -0
- checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/.zarray.__tmp1474277888848874833.~1663960300383822~ +1 -0
- checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/.zarray.__tmp16392371575518041735.~1663960300724949~ +1 -0
- checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/.zarray.__tmp16951272997414810278.~1663960300602294~ +1 -0
- checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.3 +3 -0
- checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/.zarray.__tmp10288110859122373183.~1663960300865038~ +1 -0
- checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/.zarray.__tmp11682639687068979717.~1663960300774902~ +1 -0
- checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/.zarray.__tmp16068965381288269040.~1663960300500628~ +1 -0
- checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/.zarray.__tmp16308745019235373243.~1663960300728378~ +1 -0
.gitattributes
CHANGED
|
@@ -1343,3 +1343,51 @@ checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.1 filter=lfs diff=
|
|
| 1343 |
checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 1344 |
checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1345 |
checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1343 |
checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 1344 |
checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1345 |
checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 1346 |
+
checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 1347 |
+
checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1348 |
+
checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1349 |
+
checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 1350 |
+
checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
| 1351 |
+
checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1352 |
+
checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1353 |
+
checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1354 |
+
checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
| 1355 |
+
checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
| 1356 |
+
checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1357 |
+
checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
| 1358 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1359 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 1360 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1361 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 1362 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 1363 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1364 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1365 |
+
checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 1366 |
+
checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1367 |
+
checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 1368 |
+
checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1369 |
+
checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 1370 |
+
checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 1371 |
+
checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1372 |
+
checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1373 |
+
checkpoint_1007000/target.encoder.layers_9.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 1374 |
+
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
| 1375 |
+
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1376 |
+
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1377 |
+
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1378 |
+
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
| 1379 |
+
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
| 1380 |
+
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1381 |
+
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
| 1382 |
+
checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1383 |
+
checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 1384 |
+
checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1385 |
+
checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 1386 |
+
checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 1387 |
+
checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1388 |
+
checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1389 |
+
checkpoint_1007000/target.encoder.layers_1.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 1390 |
+
checkpoint_1007000/target.encoder.layers_11.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
| 1391 |
+
checkpoint_1007000/target.encoder.layers_11.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1392 |
+
checkpoint_1007000/target.encoder.layers_11.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1393 |
+
checkpoint_1007000/target.encoder.layers_11.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
checkpoint_1007000/state.param_states.encoder.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.encoder.layers_13.pre_mlp_layer_norm.scale.v/0
ADDED
|
Binary file (15.2 kB). View file
|
|
|
checkpoint_1007000/target.decoder.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.decoder.layers_15.pre_mlp_layer_norm.scale/0
ADDED
|
Binary file (14.4 kB). View file
|
|
|
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_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_16.encoder_decoder_attention.out.kernel/.zarray.__tmp14026161881874612929.~1663960300423164~
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_16.encoder_decoder_attention.out.kernel/.zarray.__tmp14669013644749652312.~1663960300822625~
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_16.encoder_decoder_attention.out.kernel/.zarray.__tmp18190767523125055035.~1663960300683840~
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_16.encoder_decoder_attention.out.kernel/.zarray.__tmp4157870226440063089.~1663960300631997~
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_16.encoder_decoder_attention.out.kernel/.zarray.__tmp557031704751848400.~1663960300468619~
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_16.encoder_decoder_attention.out.kernel/.zarray.__tmp7489622347298658804.~1663960300313373~
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_16.encoder_decoder_attention.out.kernel/.zarray.__tmp7961904283916720111.~1663960300549206~
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_16.encoder_decoder_attention.out.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9564e3f75fec32dd962611187b146658ba78d7865f6ba85a06cce5deafa8b68
|
| 3 |
+
size 7810430
|
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96a0ea04ca381c29be403ad410f8eebdc3724c14c246f30bcdb3aa2d8896801c
|
| 3 |
+
size 7805122
|
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a143d20511e85cbfa15b853d0d3ad040680b58d5e7db684211da043f1383777e
|
| 3 |
+
size 7807257
|
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff51a903a00741679edc9619dba1affbbef0e991f5d17f4b4acdc6c7a989163c
|
| 3 |
+
size 7807962
|
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/4.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61be4cebf2d9cfa2c4b997d4eff2384aaacc07260a7bcba139233225b6b52f5f
|
| 3 |
+
size 7809108
|
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/5.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e94ae9d89c313361c894fd3751311148e586ac2a9155fa063a9db6b79ae68645
|
| 3 |
+
size 7812204
|
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/6.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a54a8c1d5564be085b334a68c8773ef074e0161f645f2b8220c19dc0dae540b
|
| 3 |
+
size 7809002
|
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.out.kernel/7.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c9c36ed94171252167c0bdeaa74d55649dfe86f40dc1e47d0bd30c08b475323
|
| 3 |
+
size 7808498
|
checkpoint_1007000/target.decoder.layers_16.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_16.mlp.wo.kernel/.zarray.__tmp10299372109499927135.~1663960300549158~
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_16.mlp.wo.kernel/.zarray.__tmp11634642641137155406.~1663960300386224~
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_16.mlp.wo.kernel/.zarray.__tmp12783591421484397450.~1663960300422099~
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_16.mlp.wo.kernel/.zarray.__tmp14543171622674484344.~1663960300467496~
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_16.mlp.wo.kernel/.zarray.__tmp17111790465239777774.~1663960300549615~
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_16.mlp.wo.kernel/.zarray.__tmp6562102490701697533.~1663960300632000~
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_16.mlp.wo.kernel/.zarray.__tmp7354295375789531146.~1663960300775471~
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_16.mlp.wo.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:623a5522a900e16da841761ebab6527494ff7d583d495da30b20badc27a1efe7
|
| 3 |
+
size 19540795
|
checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b63698142a65b5c5268d21b014e04d7b152bd43f71cf937df9e2a4eefdc68d62
|
| 3 |
+
size 19540761
|
checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97c4500e3be4a32286357fa3df04a1741fd757d46dd9000627a03eccb64405b2
|
| 3 |
+
size 19540756
|
checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38a5f64d97840523f20501a4807a7a629c1016a7eff1e8d53e4f0e296ee6f02a
|
| 3 |
+
size 19541408
|
checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/4.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59da6939d791f169bd7ecf295c5e37a59c4311b214ac12aabab5f07875307fe3
|
| 3 |
+
size 19541698
|
checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/5.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c63e5c80fe8c83c2d212e440375a335d938284cf2692e20cbb2ac05dd553b21c
|
| 3 |
+
size 19541782
|
checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/6.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3c3cd460bc8d04a53d4bb5eccca15f2448e22dc3159eee310ee0836e9496263
|
| 3 |
+
size 19541403
|
checkpoint_1007000/target.decoder.layers_16.mlp.wo.kernel/7.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f561f57e521d475d935722a55198632df5b13deff93624be017e0c10ef67e99f
|
| 3 |
+
size 19540393
|
checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/.zarray.__tmp10484147404724947140.~1663960300308272~
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_18.mlp.wi_1.kernel/.zarray.__tmp1474277888848874833.~1663960300383822~
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_18.mlp.wi_1.kernel/.zarray.__tmp16392371575518041735.~1663960300724949~
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_18.mlp.wi_1.kernel/.zarray.__tmp16951272997414810278.~1663960300602294~
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_18.mlp.wi_1.kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f01eab817226b40b97a8031fab9258d44f5a9a8d3fa47feab917239fbca69515
|
| 3 |
+
size 19493116
|
checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3fd2cfd23c309a417228d02d497e057de01cc4291b845a5796ff92bec7e1e48
|
| 3 |
+
size 19494240
|
checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70210c46d01b33b5eb2be6d29b296bed4d8a91793ae9e570722c8776c1aa5b42
|
| 3 |
+
size 19495334
|
checkpoint_1007000/target.decoder.layers_18.mlp.wi_1.kernel/0.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c66a813bb7cb90df757de37f9156850205f235826bad6b6b1ac34854942fa08
|
| 3 |
+
size 19493571
|
checkpoint_1007000/target.decoder.layers_4.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_4.encoder_decoder_attention.value.kernel/.zarray.__tmp10288110859122373183.~1663960300865038~
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.value.kernel/.zarray.__tmp11682639687068979717.~1663960300774902~
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.value.kernel/.zarray.__tmp16068965381288269040.~1663960300500628~
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.value.kernel/.zarray.__tmp16308745019235373243.~1663960300728378~
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}
|