Hugging Face's logo

bigscience
/
mt0-t5x

Model card Files Community
TimeRobber commited on
Commit
62b787b
·
1 Parent(s): a1ab262

Upload part 35

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +46 -0
  2. checkpoint_1007000/state.param_states.decoder.layers_8.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  3. checkpoint_1007000/state.param_states.decoder.layers_8.pre_mlp_layer_norm.scale.v/0 +0 -0
  4. checkpoint_1007000/state.param_states.decoder.layers_8.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
  5. checkpoint_1007000/state.param_states.decoder.layers_8.pre_self_attention_layer_norm.scale.v/0 +0 -0
  6. checkpoint_1007000/state.param_states.encoder.layers_20.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  7. checkpoint_1007000/state.param_states.encoder.layers_20.pre_mlp_layer_norm.scale.v/0 +0 -0
  8. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/.zarray +1 -0
  9. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/.zarray.__tmp10806763462053625371.~1663960300686745~ +1 -0
  10. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/.zarray.__tmp11865416203242944728.~1663960300553762~ +1 -0
  11. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/.zarray.__tmp15080021842620581745.~1663960300601937~ +1 -0
  12. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/.zarray.__tmp5647331602741647760.~1663960300727676~ +1 -0
  13. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/.zarray.__tmp6582544767140529180.~1663960300599930~ +1 -0
  14. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/.zarray.__tmp7965676094458084322.~1663960300499730~ +1 -0
  15. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/.zarray.__tmp9094432707451072520.~1663960300862369~ +1 -0
  16. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/0.0 +3 -0
  17. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/1.0 +3 -0
  18. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/2.0 +3 -0
  19. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/3.0 +3 -0
  20. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/4.0 +3 -0
  21. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/5.0 +3 -0
  22. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/6.0 +3 -0
  23. checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/7.0 +3 -0
  24. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/.zarray +1 -0
  25. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/.zarray.__tmp13561299272945765070.~1663960300688554~ +1 -0
  26. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/.zarray.__tmp17124770769414515324.~1663960300984653~ +1 -0
  27. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/.zarray.__tmp1828479082548596662.~1663960300468213~ +1 -0
  28. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/.zarray.__tmp2228167971538945355.~1663960300826715~ +1 -0
  29. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/.zarray.__tmp5447228327784409765.~1663960300545687~ +1 -0
  30. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/.zarray.__tmp5599371804264760212.~1663960300551000~ +1 -0
  31. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/.zarray.__tmp7895797222845717145.~1663960300602187~ +1 -0
  32. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.0 +3 -0
  33. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.1 +3 -0
  34. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.2 +3 -0
  35. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.3 +3 -0
  36. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.4 +3 -0
  37. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.5 +3 -0
  38. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.6 +3 -0
  39. checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.7 +3 -0
  40. checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/.zarray +1 -0
  41. checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/.zarray.__tmp10472223824676095553.~1663960300492547~ +1 -0
  42. checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/.zarray.__tmp10662888288049695722.~1663960300685735~ +1 -0
  43. checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/.zarray.__tmp17123699023105718255.~1663960300550187~ +1 -0
  44. checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/.zarray.__tmp5010368828341964925.~1663960300778550~ +1 -0
  45. checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/.zarray.__tmp7391371864505375037.~1663960300941357~ +1 -0
  46. checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/.zarray.__tmp7605841986447705432.~1663960300421631~ +1 -0
  47. checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/.zarray.__tmp9118603853177216589.~1663960300548110~ +1 -0
  48. checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.0 +3 -0
  49. checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.1 +3 -0
  50. checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.2 +3 -0
.gitattributes CHANGED
@@ -1792,3 +1792,49 @@ checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.7 filter=lfs diff=l
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
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
1795
+ checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
1796
+ checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
1797
+ checkpoint_1007000/target.encoder.layers_7.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
1798
+ checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
1799
+ checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
1800
+ checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1801
+ checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
1802
+ checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
1803
+ checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
1804
+ checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
1805
+ checkpoint_1007000/target.encoder.layers_22.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
1806
+ checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
1807
+ checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
1808
+ checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1809
+ checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
1810
+ checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
1811
+ checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
1812
+ checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
1813
+ checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
1814
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
1815
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
1816
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1817
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
1818
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
1819
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
1820
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
1821
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
1822
+ checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
1823
+ checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
1824
+ checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
1825
+ checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1826
+ checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
1827
+ checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
1828
+ checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
1829
+ checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
1830
+ checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
1831
+ checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
1832
+ checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
1833
+ checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1834
+ checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
1835
+ checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
1836
+ checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
1837
+ checkpoint_1007000/target.encoder.layers_14.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
1838
+ checkpoint_1007000/target.encoder.layers_7.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
1839
+ checkpoint_1007000/target.encoder.layers_7.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
1840
+ checkpoint_1007000/target.encoder.layers_7.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoint_1007000/state.param_states.decoder.layers_8.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_8.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (14.8 kB). View file
 
checkpoint_1007000/state.param_states.decoder.layers_8.pre_self_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}
checkpoint_1007000/state.param_states.decoder.layers_8.pre_self_attention_layer_norm.scale.v/0 ADDED
Binary file (15.1 kB). View file
 
checkpoint_1007000/state.param_states.encoder.layers_20.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_20.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (14.6 kB). View file
 
checkpoint_1007000/target.decoder.layers_12.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_12.self_attention.out.kernel/.zarray.__tmp10806763462053625371.~1663960300686745~ 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_12.self_attention.out.kernel/.zarray.__tmp11865416203242944728.~1663960300553762~ 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_12.self_attention.out.kernel/.zarray.__tmp15080021842620581745.~1663960300601937~ 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_12.self_attention.out.kernel/.zarray.__tmp5647331602741647760.~1663960300727676~ 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_12.self_attention.out.kernel/.zarray.__tmp6582544767140529180.~1663960300599930~ 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_12.self_attention.out.kernel/.zarray.__tmp7965676094458084322.~1663960300499730~ 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_12.self_attention.out.kernel/.zarray.__tmp9094432707451072520.~1663960300862369~ 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_12.self_attention.out.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18925e6f662194d21d73333e1d0cca52c6367fca3dc8b574385587bd3dd44ee1
3
+ size 7818749
checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8a950ce06427de6427d51b1861e6ac29215b1f5f0281ec202d058bdab17889
3
+ size 7815491
checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fae0b19a966305bc4f79133ac3940ec0a7e9045b902fa44d28574aa18723bea
3
+ size 7818667
checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79c2e0239dc5d08f531c73194e0c3ac805ff8daadaae3a9d229f3d9c1d32c1d6
3
+ size 7819621
checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d184ff06333ca9d2d06770ae8d8af9419e574f4fd6c8c0a96adcb16aaff91cf2
3
+ size 7817245
checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:912d419c566616c5ce491e2065e436a91a45e8708813caa5718c23f3ff5f29bf
3
+ size 7816892
checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d88f22e20d4a667b712712e9d9ccf9dff801f8cd67e0915e24a64c4b622b5a8f
3
+ size 7818582
checkpoint_1007000/target.decoder.layers_12.self_attention.out.kernel/7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41dda81b7e86b68614f3a186964009d2ed3a372b4259307ae713cca728d3ae08
3
+ size 7817324
checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/.zarray.__tmp13561299272945765070.~1663960300688554~ 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_20.self_attention.key.kernel/.zarray.__tmp17124770769414515324.~1663960300984653~ 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_20.self_attention.key.kernel/.zarray.__tmp1828479082548596662.~1663960300468213~ 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_20.self_attention.key.kernel/.zarray.__tmp2228167971538945355.~1663960300826715~ 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_20.self_attention.key.kernel/.zarray.__tmp5447228327784409765.~1663960300545687~ 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_20.self_attention.key.kernel/.zarray.__tmp5599371804264760212.~1663960300551000~ 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_20.self_attention.key.kernel/.zarray.__tmp7895797222845717145.~1663960300602187~ 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_20.self_attention.key.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60455aa06c5c32df588b4fc6eab7ae58eb145021c0a02e5a233b2a092d3c85b8
3
+ size 7819870
checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ee2842692fe30972f4a5d56770d41c542e4ca7451800aeae32c9a32464ef1e
3
+ size 7810289
checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45067a6e9bc401b9ef351e833d0361f76d849e674c1ee102830b68460068410e
3
+ size 7807896
checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3ac23110722e329cdba4f05d78e47f27513cd296c71b90b7c0b6797fa64ba4
3
+ size 7809381
checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d9e0e773b274923803fb74fa08a56c6695a5195463d81a7fda8e4e156258ecd
3
+ size 7823258
checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9aa9012576ce69dd514cc3345eed19a9c226b98455948b68dbd24c4e3b36c91
3
+ size 7809117
checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf71a0ab99cdd9e2dff1d747061a1df48bff7e4e812601c91a552d6ff1fb77fb
3
+ size 7823182
checkpoint_1007000/target.decoder.layers_20.self_attention.key.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1437f622673a4adbf8256324d0ba713a0d71ed6aac9bb2fe10595fca802690d3
3
+ size 7807552
checkpoint_1007000/target.decoder.layers_22.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_22.encoder_decoder_attention.value.kernel/.zarray.__tmp10472223824676095553.~1663960300492547~ 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_22.encoder_decoder_attention.value.kernel/.zarray.__tmp10662888288049695722.~1663960300685735~ 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_22.encoder_decoder_attention.value.kernel/.zarray.__tmp17123699023105718255.~1663960300550187~ 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_22.encoder_decoder_attention.value.kernel/.zarray.__tmp5010368828341964925.~1663960300778550~ 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_22.encoder_decoder_attention.value.kernel/.zarray.__tmp7391371864505375037.~1663960300941357~ 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_22.encoder_decoder_attention.value.kernel/.zarray.__tmp7605841986447705432.~1663960300421631~ 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_22.encoder_decoder_attention.value.kernel/.zarray.__tmp9118603853177216589.~1663960300548110~ 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_22.encoder_decoder_attention.value.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90c1dfbc1d2fd46d5ee08df8e2b1177983ca308d7fceb6c3ca631238e5eb2399
3
+ size 7808431
checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01359043877b44e3db9ae7efe7d48bee651a36aba1b20fa03439b277ec2f16b5
3
+ size 7805860
checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.value.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d47c0a5417d1d9859b2baa6f82e3326b1bbeeb0a0a4c9dda6bb510f9d546405c
3
+ size 7808985