Commit
·
a1ab262
1
Parent(s):
377ee49
Upload part 34
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +45 -0
- checkpoint_1007000/state.param_states.decoder.decoder_norm.scale.v/.zarray +1 -0
- checkpoint_1007000/state.param_states.decoder.decoder_norm.scale.v/0 +0 -0
- checkpoint_1007000/state.param_states.encoder.layers_14.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoint_1007000/state.param_states.encoder.layers_14.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoint_1007000/state.param_states.encoder.layers_23.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoint_1007000/state.param_states.encoder.layers_23.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/.zarray.__tmp11449114254713163632.~1663960300221537~ +1 -0
- checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/.zarray.__tmp17821546830779248193.~1663960299885286~ +1 -0
- checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/.zarray.__tmp2108941514933569012.~1663960300175369~ +1 -0
- checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/.zarray.__tmp3238066710871445097.~1663960300271545~ +1 -0
- checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/.zarray.__tmp8445708132507270418.~1663960300013358~ +1 -0
- checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/.zarray.__tmp8468488327763247613.~1663960299882119~ +1 -0
- checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.3 +3 -0
- checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/.zarray.__tmp17745263383657699108.~1663960300385396~ +1 -0
- checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/.zarray.__tmp18237028321777365336.~1663960300351513~ +1 -0
- checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/.zarray.__tmp2783767802025929748.~1663960301028163~ +1 -0
- checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/.zarray.__tmp3470913189304698239.~1663960300090273~ +1 -0
- checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/.zarray.__tmp516767462869462002.~1663960300346344~ +1 -0
- checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/.zarray.__tmp5587336959179015481.~1663960300423957~ +1 -0
- checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/1.0 +3 -0
- checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/2.0 +3 -0
- checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/3.0 +3 -0
- checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/4.0 +3 -0
- checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/5.0 +3 -0
- checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/6.0 +3 -0
- checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/7.0 +3 -0
- checkpoint_1007000/target.decoder.layers_11.pre_cross_attention_layer_norm.scale/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_11.pre_cross_attention_layer_norm.scale/0 +0 -0
- checkpoint_1007000/target.decoder.layers_5.pre_cross_attention_layer_norm.scale/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_5.pre_cross_attention_layer_norm.scale/0 +0 -0
- checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/.zarray +1 -0
- checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/.zarray.__tmp11153012155224071357.~1663960300087953~ +1 -0
- checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/.zarray.__tmp12734165338734811076.~1663960300602896~ +1 -0
- checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/.zarray.__tmp15085265583335157289.~1663960300312150~ +1 -0
- checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/.zarray.__tmp3776360195696461000.~1663960300888508~ +1 -0
- checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/.zarray.__tmp5899034934397531092.~1663960300779643~ +1 -0
- checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/.zarray.__tmp8934367288066493758.~1663960300502573~ +1 -0
- checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/0.0 +3 -0
- checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/1.0 +3 -0
.gitattributes
CHANGED
|
@@ -1747,3 +1747,48 @@ checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.key.kernel/
|
|
| 1747 |
checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1748 |
checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1749 |
checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1747 |
checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1748 |
checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1749 |
checkpoint_1007000/target.decoder.layers_5.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 1750 |
+
checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1751 |
+
checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 1752 |
+
checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1753 |
+
checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 1754 |
+
checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 1755 |
+
checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1756 |
+
checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1757 |
+
checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 1758 |
+
checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
| 1759 |
+
checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1760 |
+
checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1761 |
+
checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1762 |
+
checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
| 1763 |
+
checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
| 1764 |
+
checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1765 |
+
checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
| 1766 |
+
checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1767 |
+
checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 1768 |
+
checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1769 |
+
checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 1770 |
+
checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 1771 |
+
checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1772 |
+
checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1773 |
+
checkpoint_1007000/target.encoder.layers_12.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 1774 |
+
checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1775 |
+
checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 1776 |
+
checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1777 |
+
checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 1778 |
+
checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 1779 |
+
checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1780 |
+
checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1781 |
+
checkpoint_1007000/target.encoder.layers_19.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 1782 |
+
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
| 1783 |
+
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1784 |
+
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1785 |
+
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1786 |
+
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
| 1787 |
+
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
| 1788 |
+
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1789 |
+
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
| 1790 |
+
checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1791 |
+
checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 1792 |
+
checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1793 |
+
checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 1794 |
+
checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
checkpoint_1007000/state.param_states.decoder.decoder_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.decoder_norm.scale.v/0
ADDED
|
Binary file (14.6 kB). View file
|
|
|
checkpoint_1007000/state.param_states.encoder.layers_14.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_14.pre_mlp_layer_norm.scale.v/0
ADDED
|
Binary file (15.2 kB). View file
|
|
|
checkpoint_1007000/state.param_states.encoder.layers_23.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_23.pre_mlp_layer_norm.scale.v/0
ADDED
|
Binary file (14.7 kB). View file
|
|
|
checkpoint_1007000/target.decoder.layers_10.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_10.self_attention.value.kernel/.zarray.__tmp11449114254713163632.~1663960300221537~
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_10.self_attention.value.kernel/.zarray.__tmp17821546830779248193.~1663960299885286~
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_10.self_attention.value.kernel/.zarray.__tmp2108941514933569012.~1663960300175369~
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_10.self_attention.value.kernel/.zarray.__tmp3238066710871445097.~1663960300271545~
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_10.self_attention.value.kernel/.zarray.__tmp8445708132507270418.~1663960300013358~
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_10.self_attention.value.kernel/.zarray.__tmp8468488327763247613.~1663960299882119~
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_10.self_attention.value.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fae4fa5f8afc1b10a9d527f8670068e8885a5cc576ccc797ee54ad55eb2a756
|
| 3 |
+
size 7817017
|
checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1365d9de3b345318056b2cd7a9d56e2ff8c47e65a1523669282dd3b6dec719b3
|
| 3 |
+
size 7836424
|
checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:153cc53afd33664c933a4570a2ecb28a97fc2b11d84ae8c9bc59fc51d2e8a91e
|
| 3 |
+
size 7823938
|
checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:699d9153d1d98bcd9ebc7b0b21757b9216d5776feac73ff9770d7eaa75e42d83
|
| 3 |
+
size 7817699
|
checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b251224be0dce5f1d1752822bf8d28487763c71fd22cdd1a0930caa79d1fa3
|
| 3 |
+
size 7834485
|
checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6ee9abb9f715073ae79e9ddaa830f829d2b18bc13f0f69ee137ff70bbd21f72
|
| 3 |
+
size 7819180
|
checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4957b8ab8b7d07ca3a2b49700b7537b3634e59d993af8eca3abc1a0ee13860a6
|
| 3 |
+
size 7818699
|
checkpoint_1007000/target.decoder.layers_10.self_attention.value.kernel/0.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52ec89ac3ac132f3baa3edb72f87a5b1797471c0bb1c10350c8fcc8e4e38006a
|
| 3 |
+
size 7824855
|
checkpoint_1007000/target.decoder.layers_11.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_11.mlp.wo.kernel/.zarray.__tmp17745263383657699108.~1663960300385396~
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_11.mlp.wo.kernel/.zarray.__tmp18237028321777365336.~1663960300351513~
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_11.mlp.wo.kernel/.zarray.__tmp2783767802025929748.~1663960301028163~
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_11.mlp.wo.kernel/.zarray.__tmp3470913189304698239.~1663960300090273~
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_11.mlp.wo.kernel/.zarray.__tmp516767462869462002.~1663960300346344~
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_11.mlp.wo.kernel/.zarray.__tmp5587336959179015481.~1663960300423957~
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_11.mlp.wo.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f354a94e1cea421ecb6d3c227dc1e2064978901228b699a639efe37efb6af6ea
|
| 3 |
+
size 19547565
|
checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1aff78eb571952c6d3402bb78c29d6dca2c8ffe28819e0935dfac8bb6b9574e3
|
| 3 |
+
size 19547401
|
checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fe821c5eeca5ac467b8b13f1be67ec0cf3d08d7bdd81ff6295f4e23d25ff6e0
|
| 3 |
+
size 19548762
|
checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f7ebcfc6ae53a062de491bb0484e41cb3f9103250629fc8b45957618a0756ce
|
| 3 |
+
size 19547073
|
checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/4.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:006515066ccdb33784e9ef190f0545a97dd92097cc768fa4ec43312ee9011428
|
| 3 |
+
size 19548410
|
checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/5.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dce0970af821b84749a74ed27dbfc86297fb00495a78c5cf63b6303a2883035
|
| 3 |
+
size 19547953
|
checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/6.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:503b359e8ed21dd5e957085cac86a2ba4d3887e9292b3c908c3995e1f2ab22a8
|
| 3 |
+
size 19546632
|
checkpoint_1007000/target.decoder.layers_11.mlp.wo.kernel/7.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80ea00a83cac23f8b3a85ab1e7b7fb7aff698354af6a9bc0397f6698dc2e973b
|
| 3 |
+
size 19547681
|
checkpoint_1007000/target.decoder.layers_11.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_11.pre_cross_attention_layer_norm.scale/0
ADDED
|
Binary file (14.8 kB). View file
|
|
|
checkpoint_1007000/target.decoder.layers_5.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_5.pre_cross_attention_layer_norm.scale/0
ADDED
|
Binary file (14.9 kB). View file
|
|
|
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/.zarray
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[512,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/.zarray.__tmp11153012155224071357.~1663960300087953~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[512,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/.zarray.__tmp12734165338734811076.~1663960300602896~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[512,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/.zarray.__tmp15085265583335157289.~1663960300312150~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[512,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/.zarray.__tmp3776360195696461000.~1663960300888508~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[512,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/.zarray.__tmp5899034934397531092.~1663960300779643~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[512,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/.zarray.__tmp8934367288066493758.~1663960300502573~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[512,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56efd3ea2c97c07b5b89858b31073a8ba0e6244353c344d546c79370363564bf
|
| 3 |
+
size 7808964
|
checkpoint_1007000/target.encoder.layers_0.attention.out.kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74477c18d02bbda0e71e43efafe2706fe404161416dc3094a521cfe02c365685
|
| 3 |
+
size 7811938
|