TimeRobber commited on
Commit
960b0d6
·
1 Parent(s): 2870955

Upload part 52

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 +47 -0
  2. checkpoint_1007000/state.param_states.decoder.layers_6.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
  3. checkpoint_1007000/state.param_states.decoder.layers_6.pre_cross_attention_layer_norm.scale.v/0 +0 -0
  4. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/.zarray +1 -0
  5. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/.zarray.__tmp16920099091282482013.~1663960300272173~ +1 -0
  6. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/.zarray.__tmp2143065574367018663.~1663960300385518~ +1 -0
  7. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/.zarray.__tmp3423134982097405537.~1663960300864929~ +1 -0
  8. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/.zarray.__tmp7535776187432785611.~1663960300622219~ +1 -0
  9. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/.zarray.__tmp8314379597873525117.~1663960300546036~ +1 -0
  10. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/.zarray.__tmp9704787166903687556.~1663960300546727~ +1 -0
  11. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/.zarray.__tmp9962650091898432120.~1663960300729759~ +1 -0
  12. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.0 +3 -0
  13. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.1 +3 -0
  14. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.2 +3 -0
  15. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.3 +3 -0
  16. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.4 +3 -0
  17. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.5 +3 -0
  18. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.6 +3 -0
  19. checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.7 +3 -0
  20. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/.zarray +1 -0
  21. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/.zarray.__tmp10077277804349618732.~1663960300626086~ +1 -0
  22. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/.zarray.__tmp12144678259748973670.~1663960300730466~ +1 -0
  23. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/.zarray.__tmp12554898489007358719.~1663960300936600~ +1 -0
  24. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/.zarray.__tmp7284171488051620261.~1663960300865596~ +1 -0
  25. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/.zarray.__tmp8336263053539976292.~1663960300862112~ +1 -0
  26. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/.zarray.__tmp8520280910057552210.~1663960300685797~ +1 -0
  27. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/.zarray.__tmp9717176604652452474.~1663960300727766~ +1 -0
  28. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.0 +3 -0
  29. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.1 +3 -0
  30. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.2 +3 -0
  31. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.3 +3 -0
  32. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.4 +3 -0
  33. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.5 +3 -0
  34. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.6 +3 -0
  35. checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.7 +3 -0
  36. checkpoint_1007000/target.decoder.layers_18.pre_mlp_layer_norm.scale/.zarray +1 -0
  37. checkpoint_1007000/target.decoder.layers_18.pre_mlp_layer_norm.scale/0 +0 -0
  38. checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/.zarray +1 -0
  39. checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/.zarray.__tmp15695143277233168063.~1663960300420712~ +1 -0
  40. checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/.zarray.__tmp770986354543937524.~1663960300466504~ +1 -0
  41. checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/.zarray.__tmp7915233647119988176.~1663960300500932~ +1 -0
  42. checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/4.0 +3 -0
  43. checkpoint_1007000/target.encoder.layers_14.pre_mlp_layer_norm.scale/.zarray +1 -0
  44. checkpoint_1007000/target.encoder.layers_14.pre_mlp_layer_norm.scale/0 +0 -0
  45. checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/.zarray +1 -0
  46. checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/.zarray.__tmp11607415813447589211.~1663960300688829~ +1 -0
  47. checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/.zarray.__tmp13755297049538718087.~1663960300386450~ +1 -0
  48. checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/.zarray.__tmp14203396745742584940.~1663960300472379~ +1 -0
  49. checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/.zarray.__tmp14856927388036198919.~1663960300385045~ +1 -0
  50. checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/.zarray.__tmp2396571469601080444.~1663960300547679~ +1 -0
.gitattributes CHANGED
@@ -2626,3 +2626,50 @@ checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/0.0 filter=lfs diff=lf
2626
  checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
2627
  checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
2628
  checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2626
  checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
2627
  checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
2628
  checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
2629
+ checkpoint_1007000/target.decoder.layers_19.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
2630
+ checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2631
+ checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2632
+ checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2633
+ checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2634
+ checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2635
+ checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2636
+ checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2637
+ checkpoint_1007000/target.encoder.layers_20.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2638
+ checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2639
+ checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2640
+ checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2641
+ checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2642
+ checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2643
+ checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2644
+ checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2645
+ checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2646
+ checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
2647
+ checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
2648
+ checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
2649
+ checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2650
+ checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
2651
+ checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
2652
+ checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
2653
+ checkpoint_1007000/target.encoder.layers_20.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
2654
+ checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2655
+ checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2656
+ checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2657
+ checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2658
+ checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2659
+ checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2660
+ checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2661
+ checkpoint_1007000/target.encoder.layers_18.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2662
+ checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2663
+ checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2664
+ checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2665
+ checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2666
+ checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2667
+ checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2668
+ checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2669
+ checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2670
+ checkpoint_1007000/target.encoder.layers_8.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
2671
+ checkpoint_1007000/target.encoder.layers_8.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
2672
+ checkpoint_1007000/target.encoder.layers_8.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
2673
+ checkpoint_1007000/target.encoder.layers_8.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2674
+ checkpoint_1007000/target.encoder.layers_8.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
2675
+ checkpoint_1007000/target.encoder.layers_8.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
checkpoint_1007000/state.param_states.decoder.layers_6.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_6.pre_cross_attention_layer_norm.scale.v/0 ADDED
Binary file (14.8 kB). View file
 
checkpoint_1007000/target.decoder.layers_17.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_17.mlp.wi_1.kernel/.zarray.__tmp16920099091282482013.~1663960300272173~ 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_17.mlp.wi_1.kernel/.zarray.__tmp2143065574367018663.~1663960300385518~ 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_17.mlp.wi_1.kernel/.zarray.__tmp3423134982097405537.~1663960300864929~ 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_17.mlp.wi_1.kernel/.zarray.__tmp7535776187432785611.~1663960300622219~ 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_17.mlp.wi_1.kernel/.zarray.__tmp8314379597873525117.~1663960300546036~ 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_17.mlp.wi_1.kernel/.zarray.__tmp9704787166903687556.~1663960300546727~ 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_17.mlp.wi_1.kernel/.zarray.__tmp9962650091898432120.~1663960300729759~ 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_17.mlp.wi_1.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54be80960b31e67c4ddba8d215ed3e9d414cc5a355cc7aec310f63f43e0b35ce
3
+ size 19493276
checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74be137de097090deca70f290a98c1720e012d16cb3dd3fdc11f22a155a670f2
3
+ size 19493337
checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e2a1f4b68b8c16b2bc3dff943e9e35ad6e4fce0e4c2b8073249bb12f283c911
3
+ size 19492242
checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12701b15adf1eb55451b25f4011a3395208f02f64465bd06f77412195bf2692f
3
+ size 19492324
checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a9b09949bc1bb86c6161fdb944877f42143192c9456461b79c08b9cd3854c0
3
+ size 19493103
checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e150b2ef054adbde78c82897a3f87426158ef16590c90911058c4267d5159abd
3
+ size 19491658
checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50702fc1b9f2a87c2df94173d1bb90a911c28b46e2d87d0923be18d6fa6857e1
3
+ size 19492636
checkpoint_1007000/target.decoder.layers_17.mlp.wi_1.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f5b16eea7519897b6690ec51c0786bb861d3c0b6e5377aa039727de1222b4e
3
+ size 19492786
checkpoint_1007000/target.decoder.layers_18.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_18.encoder_decoder_attention.value.kernel/.zarray.__tmp10077277804349618732.~1663960300626086~ 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_18.encoder_decoder_attention.value.kernel/.zarray.__tmp12144678259748973670.~1663960300730466~ 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_18.encoder_decoder_attention.value.kernel/.zarray.__tmp12554898489007358719.~1663960300936600~ 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_18.encoder_decoder_attention.value.kernel/.zarray.__tmp7284171488051620261.~1663960300865596~ 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_18.encoder_decoder_attention.value.kernel/.zarray.__tmp8336263053539976292.~1663960300862112~ 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_18.encoder_decoder_attention.value.kernel/.zarray.__tmp8520280910057552210.~1663960300685797~ 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_18.encoder_decoder_attention.value.kernel/.zarray.__tmp9717176604652452474.~1663960300727766~ 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_18.encoder_decoder_attention.value.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e87db6b42dcf82cbe977a11725948c189612d73a2146df05325d53c6084318b6
3
+ size 7820617
checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:720e0fc4f979902a56a15aa6176122cc4e12d933e959dff81651673cf4835bfe
3
+ size 7820423
checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ab38d217724398692225686626ecfa1c0c3d61661b881898ec9883fec884a0
3
+ size 7814962
checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2762df670aee4134b9462d245bd4ff5ec0d63be4e1e8432b08c351c73eaacf7a
3
+ size 7819137
checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3e9a0201c5d5d615678379e7b3244662207c45f5943a3e6a0951ce3f67d0537
3
+ size 7818863
checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bf50ab4d125291fefa5c0c5a7d1d09c83f4b16290727324ff7975adf6c69c89
3
+ size 7819988
checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b3f867fcf3a21c8625982b550ee6e53188c71ee858517633000323c627a555
3
+ size 7821547
checkpoint_1007000/target.decoder.layers_18.encoder_decoder_attention.value.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa0fa61e85a82e87cc982932ea0e55f9e36e7ad355b2b9a394bfbf1620c039c0
3
+ size 7820267
checkpoint_1007000/target.decoder.layers_18.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_18.pre_mlp_layer_norm.scale/0 ADDED
Binary file (14 kB). View file
 
checkpoint_1007000/target.decoder.layers_19.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_19.mlp.wo.kernel/.zarray.__tmp15695143277233168063.~1663960300420712~ 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_19.mlp.wo.kernel/.zarray.__tmp770986354543937524.~1663960300466504~ 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_19.mlp.wo.kernel/.zarray.__tmp7915233647119988176.~1663960300500932~ 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_19.mlp.wo.kernel/4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53ce79648b271d0cfb303401e9c2e6a4fda4f6dea0637b06f05e86ab3fb750b5
3
+ size 19532430
checkpoint_1007000/target.encoder.layers_14.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.encoder.layers_14.pre_mlp_layer_norm.scale/0 ADDED
Binary file (14.7 kB). View file
 
checkpoint_1007000/target.encoder.layers_18.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.encoder.layers_18.attention.query.kernel/.zarray.__tmp11607415813447589211.~1663960300688829~ 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_18.attention.query.kernel/.zarray.__tmp13755297049538718087.~1663960300386450~ 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_18.attention.query.kernel/.zarray.__tmp14203396745742584940.~1663960300472379~ 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_18.attention.query.kernel/.zarray.__tmp14856927388036198919.~1663960300385045~ 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_18.attention.query.kernel/.zarray.__tmp2396571469601080444.~1663960300547679~ 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}