Hugging Face's logo

bigscience
/
mt0-t5x

Model card Files
xet
Community
TimeRobber commited on
Commit
a349b9b
·
1 Parent(s): 79e2321

Upload part 47

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 +51 -0
  2. checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/.zarray +1 -0
  3. checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/.zarray.__tmp12218884232299279589.~1663960300133903~ +1 -0
  4. checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/.zarray.__tmp14941194756017965639.~1663960300070674~ +1 -0
  5. checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/.zarray.__tmp5400868126379207817.~1663960299772734~ +1 -0
  6. checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/.zarray.__tmp5612702887125212481.~1663960299927566~ +1 -0
  7. checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/0.0 +3 -0
  8. checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/1.0 +3 -0
  9. checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/2.0 +3 -0
  10. checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/3.0 +3 -0
  11. checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/4.0 +3 -0
  12. checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/5.0 +3 -0
  13. checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/6.0 +3 -0
  14. checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/7.0 +3 -0
  15. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/.zarray +1 -0
  16. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/.zarray.__tmp12216815181697799124.~1663960300176512~ +1 -0
  17. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/.zarray.__tmp13374289530393028780.~1663960300552186~ +1 -0
  18. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/.zarray.__tmp13963848216000048093.~1663960300611187~ +1 -0
  19. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/.zarray.__tmp15451817048568847293.~1663960300271681~ +1 -0
  20. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/.zarray.__tmp18309330056829132415.~1663960300386976~ +1 -0
  21. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/.zarray.__tmp5562462019853868609.~1663960300683701~ +1 -0
  22. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.0 +3 -0
  23. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.1 +3 -0
  24. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.2 +3 -0
  25. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.3 +3 -0
  26. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.4 +3 -0
  27. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.5 +3 -0
  28. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.6 +3 -0
  29. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.7 +3 -0
  30. checkpoint_1007000/target.decoder.layers_14.pre_cross_attention_layer_norm.scale/.zarray +1 -0
  31. checkpoint_1007000/target.decoder.layers_14.pre_cross_attention_layer_norm.scale/0 +0 -0
  32. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.key.kernel/0.1 +3 -0
  33. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.key.kernel/0.7 +3 -0
  34. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/.zarray +1 -0
  35. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/.zarray.__tmp11396123514591346600.~1663960300778124~ +1 -0
  36. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/.zarray.__tmp18007055155190721889.~1663960300425181~ +1 -0
  37. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/.zarray.__tmp1910264930772778590.~1663960300822992~ +1 -0
  38. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/.zarray.__tmp2491369120114038990.~1663960300825815~ +1 -0
  39. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/.zarray.__tmp7190487690778074596.~1663960300420755~ +1 -0
  40. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/.zarray.__tmp8903546669232540215.~1663960300685285~ +1 -0
  41. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/.zarray.__tmp9363782548216798968.~1663960300351129~ +1 -0
  42. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.0 +3 -0
  43. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.1 +3 -0
  44. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.2 +3 -0
  45. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.3 +3 -0
  46. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.4 +3 -0
  47. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.5 +3 -0
  48. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.6 +3 -0
  49. checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.7 +3 -0
  50. checkpoint_1007000/target.decoder.layers_21.pre_cross_attention_layer_norm.scale/.zarray +1 -0
.gitattributes CHANGED
@@ -2386,3 +2386,54 @@ checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.6 filter=lf
2386
  checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2387
  checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2388
  checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2386
  checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2387
  checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2388
  checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2389
+ checkpoint_1007000/target.encoder.layers_15.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2390
+ checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
2391
+ checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
2392
+ checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
2393
+ checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2394
+ checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
2395
+ checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
2396
+ checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
2397
+ checkpoint_1007000/target.decoder.layers_8.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
2398
+ checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
2399
+ checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
2400
+ checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
2401
+ checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2402
+ checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
2403
+ checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
2404
+ checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
2405
+ checkpoint_1007000/target.encoder.layers_22.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
2406
+ checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
2407
+ checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
2408
+ checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
2409
+ checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2410
+ checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
2411
+ checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
2412
+ checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
2413
+ checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
2414
+ checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2415
+ checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2416
+ checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2417
+ checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2418
+ checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2419
+ checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2420
+ checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2421
+ checkpoint_1007000/target.decoder.layers_22.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2422
+ checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2423
+ checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2424
+ checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2425
+ checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2426
+ checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2427
+ checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2428
+ checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2429
+ checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2430
+ checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2431
+ checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2432
+ checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2433
+ checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2434
+ checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2435
+ checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2436
+ checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2437
+ checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2438
+ checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2439
+ checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[1280,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[10240,4096],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/.zarray.__tmp12218884232299279589.~1663960300133903~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[1280,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[10240,4096],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/.zarray.__tmp14941194756017965639.~1663960300070674~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[1280,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[10240,4096],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/.zarray.__tmp5400868126379207817.~1663960299772734~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[1280,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[10240,4096],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/.zarray.__tmp5612702887125212481.~1663960299927566~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[1280,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[10240,4096],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04ca19ba55e73a5549a9b4c53f0631431d75d8ea29136b797c9a98e480ba230b
3
+ size 19521234
checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d898f3f3d4200c76c6b6689c182ceb6a8ba0599eac3941750c48d3f615883df
3
+ size 19522338
checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b252906c706bf693ff45f78c602824b797a85a3ebecd3ccbe6bdee030138189
3
+ size 19521704
checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83c246db933aced328ff29cdd5b4a71341c668e634284caf481623ab1f46de8e
3
+ size 19521287
checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b2960d6b9c8515f7936514043a0647adfeb8dcad85e642963d9413468a1f5e
3
+ size 19521717
checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0794908afd15acc39c8c53d6f4f274bc49f27bae44d8046d5b46ba7920edd9f7
3
+ size 19521611
checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c29556a910431f11af6cb528090921c1112268873cdb727a80f398a73efb9f
3
+ size 19521401
checkpoint_1007000/target.decoder.layers_1.mlp.wo.kernel/7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f53e1af7da25ea060155e561f08b38f262d65cacc9aa228dc51b06cb0597d5
3
+ size 19520245
checkpoint_1007000/target.decoder.layers_14.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_14.encoder_decoder_attention.query.kernel/.zarray.__tmp12216815181697799124.~1663960300176512~ 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_14.encoder_decoder_attention.query.kernel/.zarray.__tmp13374289530393028780.~1663960300552186~ 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_14.encoder_decoder_attention.query.kernel/.zarray.__tmp13963848216000048093.~1663960300611187~ 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_14.encoder_decoder_attention.query.kernel/.zarray.__tmp15451817048568847293.~1663960300271681~ 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_14.encoder_decoder_attention.query.kernel/.zarray.__tmp18309330056829132415.~1663960300386976~ 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_14.encoder_decoder_attention.query.kernel/.zarray.__tmp5562462019853868609.~1663960300683701~ 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_14.encoder_decoder_attention.query.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ccf8dbcc05427c8ce5322a4998350a5814912b0c497952487ad24fa459140d
3
+ size 7802407
checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15117cfa4b3b89f74cdbf957aada27f239d678c4823a7ebaa923f6e71e33cd8a
3
+ size 7802569
checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0068fee11e5caac78d26cef35edc81e6309f7565cc2a260895fac00120dab9f8
3
+ size 7803166
checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c20275f035fab2df6830791bf847ccced49af034cfe4e1c62b67cf52d208f1c
3
+ size 7802045
checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:704ec143b40faed63bb10d297df67ff7233367448e48f10f1cef68bab7b6d9e3
3
+ size 7802017
checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0950bb8d3cccd5c74cd43cd031a386e60762528ccc3ce36bf121c94abaf62a0e
3
+ size 7801084
checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a94386d339a18ae7f286197c1619b573b551908ad35519c41138ae2d146deb
3
+ size 7801624
checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.query.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c48da83ebd94ce189d6756786b870589574e962466a3470f90eaa0c72d26167d
3
+ size 7803768
checkpoint_1007000/target.decoder.layers_14.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_14.pre_cross_attention_layer_norm.scale/0 ADDED
Binary file (14.7 kB). View file
 
checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.key.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff488b8d8168eef5a48b5688a0e5e3af4344db008ba0ce50ce05e1a8903a8d63
3
+ size 7801465
checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.key.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e38b92f531255f8055158d4fc8c06e4f8f9b6cde44db6f6e27efe0ecc2cfe8e1
3
+ size 7802817
checkpoint_1007000/target.decoder.layers_2.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_2.encoder_decoder_attention.value.kernel/.zarray.__tmp11396123514591346600.~1663960300778124~ 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_2.encoder_decoder_attention.value.kernel/.zarray.__tmp18007055155190721889.~1663960300425181~ 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_2.encoder_decoder_attention.value.kernel/.zarray.__tmp1910264930772778590.~1663960300822992~ 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_2.encoder_decoder_attention.value.kernel/.zarray.__tmp2491369120114038990.~1663960300825815~ 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_2.encoder_decoder_attention.value.kernel/.zarray.__tmp7190487690778074596.~1663960300420755~ 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_2.encoder_decoder_attention.value.kernel/.zarray.__tmp8903546669232540215.~1663960300685285~ 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_2.encoder_decoder_attention.value.kernel/.zarray.__tmp9363782548216798968.~1663960300351129~ 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_2.encoder_decoder_attention.value.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14063a6ebc5a1ccf71fb58587624723c60fef55b97e1b0ebabc5d6cb55df75e8
3
+ size 7818584
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89d3fa298c9dcdf51a64afd25c890a90a386d39c8e7732a37f9ca0f590d6d5c2
3
+ size 7818842
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f8e004988bb171ca19cbf71e4ece976100a5929f4cf72554773517773d10f8
3
+ size 7815657
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90886fbdfffd11f413a57cddeed1d0a8ac310308e0b36d425ead307301974c51
3
+ size 7815085
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5e5abbafddbec31237b338000c346a42f826ca64a77d15b6885fb1ceb5140f2
3
+ size 7816786
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a166e411f58ed72a2707e96aa7b933c2ae6b2232d76730766fcbee44ce5f451
3
+ size 7817379
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1c3d36106a867e52327aaeb2a2f50e7503db6f658dc68d9b221605635b01787
3
+ size 7816160
checkpoint_1007000/target.decoder.layers_2.encoder_decoder_attention.value.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9b544cd7926429d176f2fddb57497598f2671f7526800339225a429331745f8
3
+ size 7815159
checkpoint_1007000/target.decoder.layers_21.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}