Hugging Face's logo

bigscience
/
mt0-t5x

Model card Files Community
TimeRobber commited on
Commit
ffa5744
·
1 Parent(s): e52057c

Upload part 60

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 +38 -0
  2. checkpoint_1007000/state.param_states.decoder.layers_18.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
  3. checkpoint_1007000/state.param_states.decoder.layers_18.pre_self_attention_layer_norm.scale.v/0 +0 -0
  4. checkpoint_1007000/state.param_states.encoder.layers_0.pre_attention_layer_norm.scale.v/.zarray +1 -0
  5. checkpoint_1007000/state.param_states.encoder.layers_0.pre_attention_layer_norm.scale.v/0 +0 -0
  6. checkpoint_1007000/state.param_states.encoder.layers_1.pre_attention_layer_norm.scale.v/.zarray +1 -0
  7. checkpoint_1007000/state.param_states.encoder.layers_1.pre_attention_layer_norm.scale.v/0 +0 -0
  8. checkpoint_1007000/state.param_states.encoder.layers_17.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  9. checkpoint_1007000/state.param_states.encoder.layers_17.pre_mlp_layer_norm.scale.v/0 +0 -0
  10. checkpoint_1007000/state.param_states.encoder.layers_21.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  11. checkpoint_1007000/state.param_states.encoder.layers_21.pre_mlp_layer_norm.scale.v/0 +0 -0
  12. checkpoint_1007000/state.param_states.encoder.layers_3.pre_attention_layer_norm.scale.v/.zarray +1 -0
  13. checkpoint_1007000/state.param_states.encoder.layers_3.pre_attention_layer_norm.scale.v/0 +0 -0
  14. checkpoint_1007000/state.param_states.encoder.layers_5.pre_attention_layer_norm.scale.v/.zarray +1 -0
  15. checkpoint_1007000/state.param_states.encoder.layers_5.pre_attention_layer_norm.scale.v/0 +0 -0
  16. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray +1 -0
  17. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray.__tmp10754512409053874396.~1663960300075311~ +1 -0
  18. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray.__tmp12563961166281958174.~1663960300070979~ +1 -0
  19. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray.__tmp13622309925803484404.~1663960300984502~ +1 -0
  20. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray.__tmp14711681680530828402.~1663960299724693~ +1 -0
  21. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray.__tmp16639315334819505927.~1663960299883611~ +1 -0
  22. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray.__tmp18035412608306539123.~1663960300551592~ +1 -0
  23. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray.__tmp740425212857386636.~1663960300017812~ +1 -0
  24. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/0.0 +0 -0
  25. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/1.0 +0 -0
  26. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/2.0 +0 -0
  27. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/3.0 +0 -0
  28. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/4.0 +0 -0
  29. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/5.0 +0 -0
  30. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/6.0 +0 -0
  31. checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/7.0 +0 -0
  32. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/.zarray +1 -0
  33. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/.zarray.__tmp10563478934935647705.~1663960300550739~ +1 -0
  34. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/.zarray.__tmp10753483628268065073.~1663960300547101~ +1 -0
  35. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/.zarray.__tmp13006498700531532500.~1663960300465815~ +1 -0
  36. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/.zarray.__tmp13577582508913468553.~1663960300777576~ +1 -0
  37. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/.zarray.__tmp13602341713905738386.~1663960300822476~ +1 -0
  38. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/.zarray.__tmp18118612503057897508.~1663960300683958~ +1 -0
  39. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/.zarray.__tmp7913399995462661856.~1663960300730824~ +1 -0
  40. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/0.0 +3 -0
  41. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/1.0 +3 -0
  42. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/2.0 +3 -0
  43. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/3.0 +3 -0
  44. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/4.0 +3 -0
  45. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/5.0 +3 -0
  46. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/6.0 +3 -0
  47. checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/7.0 +3 -0
  48. checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/.zarray +1 -0
  49. checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/.zarray.__tmp10024096564966364960.~1663960300468324~ +1 -0
  50. checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/.zarray.__tmp11840796513921663008.~1663960300420606~ +1 -0
.gitattributes CHANGED
@@ -3018,3 +3018,41 @@ checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.6 filter=
3018
  checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3019
  checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3020
  checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3018
  checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3019
  checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3020
  checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3021
+ checkpoint_1007000/target.decoder.layers_7.self_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
3022
+ checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
3023
+ checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
3024
+ checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
3025
+ checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3026
+ checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
3027
+ checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
3028
+ checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
3029
+ checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
3030
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
3031
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
3032
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
3033
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3034
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
3035
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
3036
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
3037
+ checkpoint_1007000/target.decoder.layers_22.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
3038
+ checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
3039
+ checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
3040
+ checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3041
+ checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
3042
+ checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3043
+ checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3044
+ checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3045
+ checkpoint_1007000/target.decoder.layers_16.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
3046
+ checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
3047
+ checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
3048
+ checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3049
+ checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
3050
+ checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3051
+ checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3052
+ checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3053
+ checkpoint_1007000/target.decoder.layers_19.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
3054
+ checkpoint_1007000/target.encoder.layers_22.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
3055
+ checkpoint_1007000/target.encoder.layers_22.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
3056
+ checkpoint_1007000/target.encoder.layers_22.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
3057
+ checkpoint_1007000/target.encoder.layers_22.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3058
+ checkpoint_1007000/target.encoder.layers_22.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
checkpoint_1007000/state.param_states.decoder.layers_18.pre_self_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}
checkpoint_1007000/state.param_states.decoder.layers_18.pre_self_attention_layer_norm.scale.v/0 ADDED
Binary file (14.8 kB). View file
 
checkpoint_1007000/state.param_states.encoder.layers_0.pre_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.encoder.layers_0.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (15.3 kB). View file
 
checkpoint_1007000/state.param_states.encoder.layers_1.pre_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.encoder.layers_1.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (15.3 kB). View file
 
checkpoint_1007000/state.param_states.encoder.layers_17.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_17.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (15.1 kB). View file
 
checkpoint_1007000/state.param_states.encoder.layers_21.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_21.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (14.6 kB). View file
 
checkpoint_1007000/state.param_states.encoder.layers_3.pre_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.encoder.layers_3.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (15.3 kB). View file
 
checkpoint_1007000/state.param_states.encoder.layers_5.pre_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.encoder.layers_5.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (15.3 kB). View file
 
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[8,32],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[64,32],"zarr_format":2}
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray.__tmp10754512409053874396.~1663960300075311~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[8,32],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[64,32],"zarr_format":2}
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray.__tmp12563961166281958174.~1663960300070979~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[8,32],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[64,32],"zarr_format":2}
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray.__tmp13622309925803484404.~1663960300984502~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[8,32],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[64,32],"zarr_format":2}
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray.__tmp14711681680530828402.~1663960299724693~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[8,32],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[64,32],"zarr_format":2}
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray.__tmp16639315334819505927.~1663960299883611~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[8,32],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[64,32],"zarr_format":2}
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray.__tmp18035412608306539123.~1663960300551592~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[8,32],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[64,32],"zarr_format":2}
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/.zarray.__tmp740425212857386636.~1663960300017812~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[8,32],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[64,32],"zarr_format":2}
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/0.0 ADDED
Binary file (1.04 kB). View file
 
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/1.0 ADDED
Binary file (1.04 kB). View file
 
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/2.0 ADDED
Binary file (1.03 kB). View file
 
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/3.0 ADDED
Binary file (1.04 kB). View file
 
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/4.0 ADDED
Binary file (1.03 kB). View file
 
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/5.0 ADDED
Binary file (1.03 kB). View file
 
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/6.0 ADDED
Binary file (1.04 kB). View file
 
checkpoint_1007000/state.param_states.encoder.relpos_bias.rel_embedding.v/7.0 ADDED
Binary file (1.04 kB). View file
 
checkpoint_1007000/target.decoder.layers_15.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_15.self_attention.out.kernel/.zarray.__tmp10563478934935647705.~1663960300550739~ 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_15.self_attention.out.kernel/.zarray.__tmp10753483628268065073.~1663960300547101~ 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_15.self_attention.out.kernel/.zarray.__tmp13006498700531532500.~1663960300465815~ 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_15.self_attention.out.kernel/.zarray.__tmp13577582508913468553.~1663960300777576~ 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_15.self_attention.out.kernel/.zarray.__tmp13602341713905738386.~1663960300822476~ 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_15.self_attention.out.kernel/.zarray.__tmp18118612503057897508.~1663960300683958~ 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_15.self_attention.out.kernel/.zarray.__tmp7913399995462661856.~1663960300730824~ 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_15.self_attention.out.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8430ba8c5ab65c34a90fe723f61278d803722f99914dd8535ccada9242b34e7
3
+ size 7817920
checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6042be4eab8e395c687ae94a41e1dbb6c279482bc39720e04131bbb6284439b7
3
+ size 7817923
checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeb19b262d31de4a30d7d3688f9bb51a9a8cd21761b7f6a456dcb369422d3361
3
+ size 7816317
checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:173cc6385b061768a6605e3231359cd99db7d523409362af925647f4c6c0b724
3
+ size 7817958
checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0813195df513bf2bf76b9c35887aa7840da2098a9d4df3fe5f620e88f1dd74c
3
+ size 7816628
checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1137255bf2cb83b966420834837dc1db520ca1b97bf29cfd1dc6a13870c7169
3
+ size 7818152
checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0ae882ae44e45a2702ef9f11b7e4ca132c89e6964d43267b8ea14279382415a
3
+ size 7813505
checkpoint_1007000/target.decoder.layers_15.self_attention.out.kernel/7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a398c624b2da3608532091ea02b383840ea4686f08064094ee5eeff0aa3ea2e0
3
+ size 7815049
checkpoint_1007000/target.decoder.layers_16.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_16.mlp.wi_1.kernel/.zarray.__tmp10024096564966364960.~1663960300468324~ 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_16.mlp.wi_1.kernel/.zarray.__tmp11840796513921663008.~1663960300420606~ 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}