Commit
·
86d19a5
1
Parent(s):
b4094ee
Upload part 58
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.decoder.layers_16.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoint_1007000/state.param_states.decoder.layers_16.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoint_1007000/state.param_states.encoder.layers_5.pre_mlp_layer_norm.scale.v/.zarray +1 -0
- checkpoint_1007000/state.param_states.encoder.layers_5.pre_mlp_layer_norm.scale.v/0 +0 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/.zarray.__tmp10791279507588641790.~1663960300986493~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/.zarray.__tmp13087716466617685678.~1663960300552176~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/.zarray.__tmp14443261782001258942.~1663960300465669~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/.zarray.__tmp15740594840837912186.~1663960300088141~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/.zarray.__tmp15827049849721584044.~1663960300073159~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/.zarray.__tmp16579121510195704754.~1663960299927726~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/.zarray.__tmp177333778408477115.~1663960300018099~ +1 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.3 +3 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/.zarray.__tmp13711390006315871755.~1663960300628435~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/.zarray.__tmp15405411141927448681.~1663960300683564~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/.zarray.__tmp18312115719260556282.~1663960300466382~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/.zarray.__tmp4537385026586841120.~1663960300727472~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/.zarray.__tmp7256889655898870113.~1663960300862363~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/.zarray.__tmp9136934180551425698.~1663960300468407~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/.zarray.__tmp9229006870196262440.~1663960300600964~ +1 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.3 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_2.pre_cross_attention_layer_norm.scale/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_2.pre_cross_attention_layer_norm.scale/0 +0 -0
- checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/.zarray.__tmp7013055452811087124.~1663960300550706~ +1 -0
- checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/.zarray.__tmp14811787249835243730.~1663960300599358~ +1 -0
- checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/.zarray.__tmp15810625716880545097.~1663960300550548~ +1 -0
- checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/.zarray.__tmp17844317229516739086.~1663960300500090~ +1 -0
- checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/.zarray.__tmp17969033712181709035.~1663960300420539~ +1 -0
.gitattributes
CHANGED
@@ -2919,3 +2919,51 @@ checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.1 filter=lfs diff=
|
|
2919 |
checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
2920 |
checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
2921 |
checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2919 |
checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
2920 |
checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
2921 |
checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
2922 |
+
checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
2923 |
+
checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
2924 |
+
checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
2925 |
+
checkpoint_1007000/target.encoder.layers_15.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
2926 |
+
checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
2927 |
+
checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
2928 |
+
checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
2929 |
+
checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
2930 |
+
checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
2931 |
+
checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
2932 |
+
checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
2933 |
+
checkpoint_1007000/target.decoder.layers_7.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
2934 |
+
checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
|
2935 |
+
checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
2936 |
+
checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
2937 |
+
checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
2938 |
+
checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
|
2939 |
+
checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
|
2940 |
+
checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
2941 |
+
checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
|
2942 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
2943 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
2944 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
2945 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
2946 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
2947 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
2948 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
2949 |
+
checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
2950 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
2951 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
2952 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
2953 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
2954 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
2955 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
2956 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
2957 |
+
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
2958 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
2959 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
2960 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
2961 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
2962 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
2963 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
2964 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
2965 |
+
checkpoint_1007000/target.decoder.layers_6.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
2966 |
+
checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
2967 |
+
checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
2968 |
+
checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
2969 |
+
checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
checkpoint_1007000/state.param_states.decoder.layers_16.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_16.pre_mlp_layer_norm.scale.v/0
ADDED
Binary file (14.9 kB). View file
|
|
checkpoint_1007000/state.param_states.encoder.layers_5.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_5.pre_mlp_layer_norm.scale.v/0
ADDED
Binary file (15.3 kB). View file
|
|
checkpoint_1007000/target.decoder.layers_1.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_1.encoder_decoder_attention.query.kernel/.zarray.__tmp10791279507588641790.~1663960300986493~
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/.zarray.__tmp13087716466617685678.~1663960300552176~
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/.zarray.__tmp14443261782001258942.~1663960300465669~
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/.zarray.__tmp15740594840837912186.~1663960300088141~
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/.zarray.__tmp15827049849721584044.~1663960300073159~
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/.zarray.__tmp16579121510195704754.~1663960299927726~
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/.zarray.__tmp177333778408477115.~1663960300018099~
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd841e33cb8df42fe285d77a855507d322526ee09acead07525dac137abfdc38
|
3 |
+
size 7823909
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:072171cba60a22394a34832a0924b636319a87630fd919091b7372cfbe7eb3c9
|
3 |
+
size 7831019
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72fa186433698733fa073e0408750f8fb83839991064b226da63341dec534926
|
3 |
+
size 7825456
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d61cd1b78e3800f4919c9e1c98209912077ddccbffb71f80259ced84d6a35ce5
|
3 |
+
size 7819422
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4afdbfe286448d73ecc202f70aafe1005e11405be61f6157f4b36e775bc0bc7
|
3 |
+
size 7827991
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5707ed5f6149c1ffb0c427c078ecef7e47fb41dd590dbe059978d8702eb3b545
|
3 |
+
size 7825161
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24139ebef8056ba79b500fdb4b3752743279300f960c54f71334f10555bf68e0
|
3 |
+
size 7812982
|
checkpoint_1007000/target.decoder.layers_1.encoder_decoder_attention.query.kernel/0.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39a1451ae7f8245110222ea07be9d0f407483b66a7ddbf575c6f42c25f289212
|
3 |
+
size 7806743
|
checkpoint_1007000/target.decoder.layers_12.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_12.self_attention.value.kernel/.zarray.__tmp13711390006315871755.~1663960300628435~
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.value.kernel/.zarray.__tmp15405411141927448681.~1663960300683564~
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.value.kernel/.zarray.__tmp18312115719260556282.~1663960300466382~
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.value.kernel/.zarray.__tmp4537385026586841120.~1663960300727472~
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.value.kernel/.zarray.__tmp7256889655898870113.~1663960300862363~
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.value.kernel/.zarray.__tmp9136934180551425698.~1663960300468407~
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.value.kernel/.zarray.__tmp9229006870196262440.~1663960300600964~
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.value.kernel/0.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68a53c095adc3f3a119d0ce07f304c05cc77c8998635647c3ad853c175b3515e
|
3 |
+
size 7813039
|
checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec810c5bf579c511af885501f3f502077508839600c485dad3b0177c049b8e5b
|
3 |
+
size 7823641
|
checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7225a5e5e368ea5d33e550a3aa630926b611a604963a7823960a953d0f7f2638
|
3 |
+
size 7817186
|
checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f73364fe3f9611794abbbc340fd2eaae0fe9cb7ad71606e02694452f66a6aa6
|
3 |
+
size 7815133
|
checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce3cebea1940c211f50bedac3377ade08df9a78d0b5e7d8b6ee622d9e34a1eff
|
3 |
+
size 7834827
|
checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:825ec278fe5d9a328c13fd9dd2055066a18c7b090fa33cc8985fbfea6c95cae8
|
3 |
+
size 7819094
|
checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e4c7cf48d06197e3dda48fb6449e803efb8fd75e3e66f63fdbac1b829bd1533
|
3 |
+
size 7824334
|
checkpoint_1007000/target.decoder.layers_12.self_attention.value.kernel/0.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5340b27dabfb54f240465ebe27f3ff69c1bdd537e4346c612611a95cb056f22f
|
3 |
+
size 7817690
|
checkpoint_1007000/target.decoder.layers_2.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_2.pre_cross_attention_layer_norm.scale/0
ADDED
Binary file (14.9 kB). View file
|
|
checkpoint_1007000/target.decoder.layers_3.encoder_decoder_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_3.encoder_decoder_attention.key.kernel/.zarray.__tmp7013055452811087124.~1663960300550706~
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_3.encoder_decoder_attention.key.kernel/0.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fd5bfd23d7d2d5a7b6a18deaaac067d0b89ead887e161dc58f543a4b1a9e599
|
3 |
+
size 7803075
|
checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebb036109bf1435395295daa1ea74285cd3a03e418bb29ab2d7a289547ddef31
|
3 |
+
size 7802120
|
checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60311da08d44985dd926fbc30e0c19b43585954e520ccab8309867e1b556c65c
|
3 |
+
size 7801528
|
checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.key.kernel/0.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a19ab0c0c4290b511a1e2a179ccd0366a0b4ecc1939b97da9b07710f13f9975
|
3 |
+
size 7806428
|
checkpoint_1007000/target.decoder.layers_6.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_6.self_attention.query.kernel/.zarray.__tmp14811787249835243730.~1663960300599358~
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_6.self_attention.query.kernel/.zarray.__tmp15810625716880545097.~1663960300550548~
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_6.self_attention.query.kernel/.zarray.__tmp17844317229516739086.~1663960300500090~
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_6.self_attention.query.kernel/.zarray.__tmp17969033712181709035.~1663960300420539~
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}
|