Hugging Face's logo

bigscience
/
mt0-t5x

Model card Files
xet
Community
TimeRobber commited on
Commit
60f6115
·
1 Parent(s): d38c4eb

Upload part 49

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 +45 -0
  2. checkpoint_1007000/state.param_states.decoder.layers_12.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
  3. checkpoint_1007000/state.param_states.decoder.layers_12.pre_cross_attention_layer_norm.scale.v/0 +0 -0
  4. checkpoint_1007000/state.param_states.encoder.encoder_norm.scale.v/.zarray +1 -0
  5. checkpoint_1007000/state.param_states.encoder.encoder_norm.scale.v/0 +0 -0
  6. checkpoint_1007000/state.param_states.encoder.layers_6.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  7. checkpoint_1007000/state.param_states.encoder.layers_6.pre_mlp_layer_norm.scale.v/0 +0 -0
  8. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/.zarray +1 -0
  9. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/.zarray.__tmp10694960163214750706.~1663960299930792~ +1 -0
  10. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/.zarray.__tmp11846436521798358021.~1663960300549025~ +1 -0
  11. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/.zarray.__tmp12858671693678598299.~1663960300175308~ +1 -0
  12. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/.zarray.__tmp16727503215663209486.~1663960300774407~ +1 -0
  13. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/.zarray.__tmp16961620167020841977.~1663960300221654~ +1 -0
  14. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/.zarray.__tmp17154788997525181103.~1663960300015189~ +1 -0
  15. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/.zarray.__tmp6151774326364145803.~1663960300175839~ +1 -0
  16. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.0 +3 -0
  17. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.1 +3 -0
  18. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.2 +3 -0
  19. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.3 +3 -0
  20. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.4 +3 -0
  21. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.5 +3 -0
  22. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.6 +3 -0
  23. checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.7 +3 -0
  24. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/.zarray.__tmp6319147771241005795.~1663960300347091~ +1 -0
  25. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.4 +3 -0
  26. checkpoint_1007000/target.decoder.layers_23.pre_mlp_layer_norm.scale/.zarray +1 -0
  27. checkpoint_1007000/target.decoder.layers_23.pre_mlp_layer_norm.scale/0 +0 -0
  28. checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/.zarray +1 -0
  29. checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/.zarray.__tmp10707391637090198780.~1663960300383836~ +1 -0
  30. checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/.zarray.__tmp12937294553889577868.~1663960300728875~ +1 -0
  31. checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/.zarray.__tmp3413639425620635111.~1663960300622118~ +1 -0
  32. checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/.zarray.__tmp6390570329606431345.~1663960300421327~ +1 -0
  33. checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/.zarray.__tmp8916467731617070710.~1663960300497635~ +1 -0
  34. checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.0 +3 -0
  35. checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.1 +3 -0
  36. checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.6 +3 -0
  37. checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.7 +3 -0
  38. checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/.zarray +1 -0
  39. checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/.zarray.__tmp11133685423862926574.~1663960300547591~ +1 -0
  40. checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/.zarray.__tmp4453613379638851411.~1663960300421702~ +1 -0
  41. checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/.zarray.__tmp6072601774882511910.~1663960300468273~ +1 -0
  42. checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/.zarray.__tmp684952820793828258.~1663960300386206~ +1 -0
  43. checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/.zarray.__tmp6936183393611851112.~1663960300728891~ +1 -0
  44. checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/.zarray.__tmp7420214262949702740.~1663960300873666~ +1 -0
  45. checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/.zarray.__tmp9272436304647770054.~1663960300688378~ +1 -0
  46. checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.0 +3 -0
  47. checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.1 +3 -0
  48. checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.2 +3 -0
  49. checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.3 +3 -0
  50. checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.4 +3 -0
.gitattributes CHANGED
@@ -2482,3 +2482,48 @@ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel
2482
  checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2483
  checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2484
  checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2482
  checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2483
  checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2484
  checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2485
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2486
+ checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
2487
+ checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
2488
+ checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
2489
+ checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2490
+ checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
2491
+ checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
2492
+ checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
2493
+ checkpoint_1007000/target.encoder.layers_7.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
2494
+ checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2495
+ checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2496
+ checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2497
+ checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2498
+ checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2499
+ checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2500
+ checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2501
+ checkpoint_1007000/target.encoder.layers_23.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2502
+ checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2503
+ checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2504
+ checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2505
+ checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2506
+ checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2507
+ checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2508
+ checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2509
+ checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2510
+ checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2511
+ checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2512
+ checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2513
+ checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2514
+ checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2515
+ checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2516
+ checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2517
+ checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2518
+ checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2519
+ checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2520
+ checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2521
+ checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2522
+ checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2523
+ checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2524
+ checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2525
+ checkpoint_1007000/target.encoder.layers_17.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2526
+ checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2527
+ checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2528
+ checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2529
+ checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
checkpoint_1007000/state.param_states.decoder.layers_12.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_12.pre_cross_attention_layer_norm.scale.v/0 ADDED
Binary file (14.9 kB). View file
 
checkpoint_1007000/state.param_states.encoder.encoder_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.encoder_norm.scale.v/0 ADDED
Binary file (14.8 kB). View file
 
checkpoint_1007000/state.param_states.encoder.layers_6.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_6.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (15.3 kB). View file
 
checkpoint_1007000/target.decoder.layers_0.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_0.encoder_decoder_attention.query.kernel/.zarray.__tmp10694960163214750706.~1663960299930792~ 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_0.encoder_decoder_attention.query.kernel/.zarray.__tmp11846436521798358021.~1663960300549025~ 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_0.encoder_decoder_attention.query.kernel/.zarray.__tmp12858671693678598299.~1663960300175308~ 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_0.encoder_decoder_attention.query.kernel/.zarray.__tmp16727503215663209486.~1663960300774407~ 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_0.encoder_decoder_attention.query.kernel/.zarray.__tmp16961620167020841977.~1663960300221654~ 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_0.encoder_decoder_attention.query.kernel/.zarray.__tmp17154788997525181103.~1663960300015189~ 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_0.encoder_decoder_attention.query.kernel/.zarray.__tmp6151774326364145803.~1663960300175839~ 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_0.encoder_decoder_attention.query.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e61e3e35322a58dcca2207d12e28072c2ed56365eced28e2519c0b6a07f29b6
3
+ size 7824788
checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34735b0256b493f1939a070379ebd16ec53a4935cfda278c8ae5ac55704311ac
3
+ size 7824125
checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ed73e0045e76d57906299dd726aee95f3c14f2af461648492b305a882d1df31
3
+ size 7825288
checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e7f3bc21c538668019f792854ead8d836cae01b81eebcfda3141cf35ab24dbc
3
+ size 7821779
checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:197cbaf0a4c3910c2606114779e84c6618ff8dd48085a39b9f0bad40b5440541
3
+ size 7819972
checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f725a09ef1b74c305557da42df2578c302b95bd3f123aba09599880e8ac08bf5
3
+ size 7822536
checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb3cf3f2e995efa7da023dd731259eeda03e479a8adbeef8da8dd8b716d8539
3
+ size 7816249
checkpoint_1007000/target.decoder.layers_0.encoder_decoder_attention.query.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f555f3b40ee5657e6a49f565880566de63e9aafe19bfa503209f70893f7243eb
3
+ size 7828090
checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.key.kernel/.zarray.__tmp6319147771241005795.~1663960300347091~ 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.encoder_decoder_attention.key.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37fa59febc0bfa25f2187be004fca485f797a3e7f2e1e27c2f61c136383272e8
3
+ size 7807867
checkpoint_1007000/target.decoder.layers_23.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_23.pre_mlp_layer_norm.scale/0 ADDED
Binary file (13.9 kB). View file
 
checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/.zarray.__tmp10707391637090198780.~1663960300383836~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/.zarray.__tmp12937294553889577868.~1663960300728875~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/.zarray.__tmp3413639425620635111.~1663960300622118~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/.zarray.__tmp6390570329606431345.~1663960300421327~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/.zarray.__tmp8916467731617070710.~1663960300497635~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5af53badd4d7ff8a7f2254fdd964ae36b39c1d121867af050abf3fc3821f21ac
3
+ size 19556386
checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9652573631d87ff07a7410ea2c7d24cfad4a9777955e29846ffdfdb9fabf079
3
+ size 19554814
checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9dde20509faa72adaf8a53553935feb31ba8d14f127678b9b5633c7c74a18c1
3
+ size 19554473
checkpoint_1007000/target.decoder.layers_3.mlp.wi_1.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cddaa815e957bd1ab92d217616c5cf02f7073f890dd6e7c4f703f3181663cfc
3
+ size 19555706
checkpoint_1007000/target.decoder.layers_6.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_6.encoder_decoder_attention.value.kernel/.zarray.__tmp11133685423862926574.~1663960300547591~ 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.encoder_decoder_attention.value.kernel/.zarray.__tmp4453613379638851411.~1663960300421702~ 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.encoder_decoder_attention.value.kernel/.zarray.__tmp6072601774882511910.~1663960300468273~ 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.encoder_decoder_attention.value.kernel/.zarray.__tmp684952820793828258.~1663960300386206~ 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.encoder_decoder_attention.value.kernel/.zarray.__tmp6936183393611851112.~1663960300728891~ 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.encoder_decoder_attention.value.kernel/.zarray.__tmp7420214262949702740.~1663960300873666~ 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.encoder_decoder_attention.value.kernel/.zarray.__tmp9272436304647770054.~1663960300688378~ 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.encoder_decoder_attention.value.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91b698db548e688477662750f3ca11d672e2c138875943c43a5faf066cbd3a4
3
+ size 7821905
checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcb93ca8dc9ee66640e1e70f8c2f8663105e69e675a775a3245da1a5ac1138fd
3
+ size 7817257
checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ffdf07fbc476b3cd62bb6b671faf20c2fedad8797ea4acd49199629ca911ec
3
+ size 7816370
checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77472207dddff61ce0f2d0783f158cbefd15461ed53ea717c1d3d780bb6d8558
3
+ size 7817916
checkpoint_1007000/target.decoder.layers_6.encoder_decoder_attention.value.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fdcdaf60950bdb53ec8c2fe216565bfa704de75388e51bb66c80fb857c4d140
3
+ size 7816576