Hugging Face's logo

bigscience
/
mt0-t5x

Model card Files Community
TimeRobber commited on
Commit
5dab7b4
·
1 Parent(s): 42371b3

Upload part 72

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 +48 -0
  2. checkpoint_1007000/state.param_states.decoder.layers_23.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
  3. checkpoint_1007000/state.param_states.decoder.layers_23.pre_cross_attention_layer_norm.scale.v/0 +0 -0
  4. checkpoint_1007000/target.decoder.layers_10.pre_mlp_layer_norm.scale/.zarray +1 -0
  5. checkpoint_1007000/target.decoder.layers_10.pre_mlp_layer_norm.scale/0 +0 -0
  6. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/.zarray +1 -0
  7. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/.zarray.__tmp12933403416076715062.~1663960300890276~ +1 -0
  8. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/.zarray.__tmp13309180590195031581.~1663960300465930~ +1 -0
  9. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/.zarray.__tmp13720021343832536840.~1663960300729807~ +1 -0
  10. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/.zarray.__tmp18295870723194581808.~1663960300501537~ +1 -0
  11. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/.zarray.__tmp3125698344571142755.~1663960300549392~ +1 -0
  12. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/.zarray.__tmp8318955135197036346.~1663960300990201~ +1 -0
  13. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/.zarray.__tmp9161018588045249713.~1663960300683706~ +1 -0
  14. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.0 +3 -0
  15. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.1 +3 -0
  16. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.2 +3 -0
  17. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.3 +3 -0
  18. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.4 +3 -0
  19. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.5 +3 -0
  20. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.6 +3 -0
  21. checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.7 +3 -0
  22. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/.zarray +1 -0
  23. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/.zarray.__tmp11443457941326244834.~1663960300502456~ +1 -0
  24. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/.zarray.__tmp1585381333899632109.~1663960300467469~ +1 -0
  25. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/.zarray.__tmp1786503678491053046.~1663960300685621~ +1 -0
  26. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/.zarray.__tmp2473946226829266337.~1663960300775067~ +1 -0
  27. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/.zarray.__tmp6747097374544282232.~1663960300420929~ +1 -0
  28. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/.zarray.__tmp9091067974118765769.~1663960300548315~ +1 -0
  29. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/.zarray.__tmp9331816110739500545.~1663960300554345~ +1 -0
  30. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/0.0 +3 -0
  31. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/1.0 +3 -0
  32. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/2.0 +3 -0
  33. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/3.0 +3 -0
  34. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/4.0 +3 -0
  35. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/5.0 +3 -0
  36. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/6.0 +3 -0
  37. checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/7.0 +3 -0
  38. checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/.zarray +1 -0
  39. checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/.zarray.__tmp10290412213563372658.~1663960300686401~ +1 -0
  40. checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/.zarray.__tmp14785815517688527893.~1663960300471685~ +1 -0
  41. checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/.zarray.__tmp381659246014802317.~1663960300777185~ +1 -0
  42. checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/.zarray.__tmp4332171129744721202.~1663960300622269~ +1 -0
  43. checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/.zarray.__tmp5250181825793393275.~1663960300890454~ +1 -0
  44. checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/.zarray.__tmp7532996701969609729.~1663960300986841~ +1 -0
  45. checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/.zarray.__tmp7604966773388894770.~1663960300501187~ +1 -0
  46. checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.0 +3 -0
  47. checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.1 +3 -0
  48. checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.2 +3 -0
  49. checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.3 +3 -0
  50. checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.4 +3 -0
.gitattributes CHANGED
@@ -3555,3 +3555,51 @@ checkpoint_1007000/target.encoder.layers_0.mlp.wi_0.kernel/0.5 filter=lfs diff=l
3555
  checkpoint_1007000/target.encoder.layers_0.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3556
  checkpoint_1007000/target.encoder.layers_0.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3557
  checkpoint_1007000/target.encoder.layers_0.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3555
  checkpoint_1007000/target.encoder.layers_0.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3556
  checkpoint_1007000/target.encoder.layers_0.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3557
  checkpoint_1007000/target.encoder.layers_0.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
3558
+ checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
3559
+ checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
3560
+ checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3561
+ checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
3562
+ checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3563
+ checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3564
+ checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3565
+ checkpoint_1007000/target.encoder.layers_15.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
3566
+ checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
3567
+ checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
3568
+ checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3569
+ checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
3570
+ checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3571
+ checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3572
+ checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3573
+ checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
3574
+ checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
3575
+ checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
3576
+ checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3577
+ checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
3578
+ checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3579
+ checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3580
+ checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3581
+ checkpoint_1007000/target.encoder.layers_20.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
3582
+ checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
3583
+ checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
3584
+ checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3585
+ checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
3586
+ checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3587
+ checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3588
+ checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3589
+ checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
3590
+ checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
3591
+ checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
3592
+ checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3593
+ checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
3594
+ checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3595
+ checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3596
+ checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3597
+ checkpoint_1007000/target.encoder.layers_8.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
3598
+ checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
3599
+ checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
3600
+ checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
3601
+ checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3602
+ checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
3603
+ checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
3604
+ checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
3605
+ checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
checkpoint_1007000/state.param_states.decoder.layers_23.pre_cross_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_23.pre_cross_attention_layer_norm.scale.v/0 ADDED
Binary file (14.2 kB). View file
 
checkpoint_1007000/target.decoder.layers_10.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_10.pre_mlp_layer_norm.scale/0 ADDED
Binary file (14.8 kB). View file
 
checkpoint_1007000/target.decoder.layers_16.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_16.encoder_decoder_attention.value.kernel/.zarray.__tmp12933403416076715062.~1663960300890276~ 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_16.encoder_decoder_attention.value.kernel/.zarray.__tmp13309180590195031581.~1663960300465930~ 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_16.encoder_decoder_attention.value.kernel/.zarray.__tmp13720021343832536840.~1663960300729807~ 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_16.encoder_decoder_attention.value.kernel/.zarray.__tmp18295870723194581808.~1663960300501537~ 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_16.encoder_decoder_attention.value.kernel/.zarray.__tmp3125698344571142755.~1663960300549392~ 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_16.encoder_decoder_attention.value.kernel/.zarray.__tmp8318955135197036346.~1663960300990201~ 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_16.encoder_decoder_attention.value.kernel/.zarray.__tmp9161018588045249713.~1663960300683706~ 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_16.encoder_decoder_attention.value.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bada59e0a07c29d256b938d5ec20ddcf5b668e09b3847cce73ee90d50411829f
3
+ size 7821442
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38fecb93b8f8a30b19123e77802ff0c32f88305184f912d8884cf324c5d65f36
3
+ size 7819490
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59fc4cfbf334c18514ec2e5a857a2d464ee22400921cbcaaa7745aa80b420732
3
+ size 7818155
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7133474fcd9f0493635f438a58a0f54a96b697a69aaaa656c0eade17bfae129e
3
+ size 7817318
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5585855b4fb07073d2722bc0d0f825c8ee315f8107c1938e995833702d2636c
3
+ size 7815183
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b6dbdb8d1ca50c309ce14aa63073c6f93a89cfba87343eb866182bb310803a
3
+ size 7819146
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce978027f6f15262d8be6b24eb2548453fe06a906b4a530fb9b588578f40e7ee
3
+ size 7819273
checkpoint_1007000/target.decoder.layers_16.encoder_decoder_attention.value.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9771d87a51a3df618f2338bbd007b43186f7e704edda96404cd0076f616c6f3a
3
+ size 7819348
checkpoint_1007000/target.decoder.layers_22.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_22.self_attention.out.kernel/.zarray.__tmp11443457941326244834.~1663960300502456~ 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_22.self_attention.out.kernel/.zarray.__tmp1585381333899632109.~1663960300467469~ 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_22.self_attention.out.kernel/.zarray.__tmp1786503678491053046.~1663960300685621~ 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_22.self_attention.out.kernel/.zarray.__tmp2473946226829266337.~1663960300775067~ 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_22.self_attention.out.kernel/.zarray.__tmp6747097374544282232.~1663960300420929~ 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_22.self_attention.out.kernel/.zarray.__tmp9091067974118765769.~1663960300548315~ 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_22.self_attention.out.kernel/.zarray.__tmp9331816110739500545.~1663960300554345~ 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_22.self_attention.out.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9a0f4aed1984138b0e025a28ce4bbb35b4082cd2226929b8035da532b7788b8
3
+ size 7796179
checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:289faf3f9bd93071e6d90a3ecc29a82f6b9a1d062dbae85c2d16ccc3e2a4e3b8
3
+ size 7801782
checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ecdc3b60aa8fbd43c72d0a2abe298b20562aa3db88e95189ef7036ec258427
3
+ size 7796705
checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:667df4a8d22563c73437d91fef7fc81c72d88fb5f469ec3433452569e6446db6
3
+ size 7796162
checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e21fc06a9fb354acd0e9009f9798a1eb096030e9b046c01134821d9bf8502ea3
3
+ size 7797103
checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b19d8c33414262e3fb2bbfa5b17c1ee6ee4f8788dbd5266eed8a8263cc10751
3
+ size 7796884
checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f5981a72e008cb1c2cfe37e4e023c3df3218ba66508e4a4789b8ec7ecd80430
3
+ size 7796969
checkpoint_1007000/target.decoder.layers_22.self_attention.out.kernel/7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ef6a6b05a1c77141b129c2f75ab0bb688d0ad10d909bc79ef66448ec323f0b8
3
+ size 7795875
checkpoint_1007000/target.encoder.layers_0.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.encoder.layers_0.attention.key.kernel/.zarray.__tmp10290412213563372658.~1663960300686401~ 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.encoder.layers_0.attention.key.kernel/.zarray.__tmp14785815517688527893.~1663960300471685~ 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.encoder.layers_0.attention.key.kernel/.zarray.__tmp381659246014802317.~1663960300777185~ 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.encoder.layers_0.attention.key.kernel/.zarray.__tmp4332171129744721202.~1663960300622269~ 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.encoder.layers_0.attention.key.kernel/.zarray.__tmp5250181825793393275.~1663960300890454~ 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.encoder.layers_0.attention.key.kernel/.zarray.__tmp7532996701969609729.~1663960300986841~ 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.encoder.layers_0.attention.key.kernel/.zarray.__tmp7604966773388894770.~1663960300501187~ 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.encoder.layers_0.attention.key.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f31ddc2c3d11ccb0933ebbe32639516f28a844e3c18817cc52af4f5441556713
3
+ size 7800275
checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2093f55f2b0ed5ae16c3bf002cdcc8ccbbb8813119b76fdca31a54996f971fef
3
+ size 7804427
checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6d311e29685eb185823004d91c729276f3b53dcd70de69ec455308ccbd3490c
3
+ size 7801260
checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb16ba758106016a4f8d0505286b8d060bfda2d21ad91b6a83647b5e39f2d244
3
+ size 7805470
checkpoint_1007000/target.encoder.layers_0.attention.key.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4920bf69c6a5cc871fcfd22b42804a2c648ee80cf35b690a029ba11fbf263691
3
+ size 7803123