Hugging Face's logo

bigscience
/
mt0-t5x

Model card Files Community
TimeRobber commited on
Commit
d24e4aa
·
1 Parent(s): 81d9a5a

Upload part 1

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_0.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
  3. checkpoint_1007000/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/0 +0 -0
  4. checkpoint_1007000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
  5. checkpoint_1007000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/0 +0 -0
  6. checkpoint_1007000/state.param_states.decoder.layers_12.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  7. checkpoint_1007000/state.param_states.decoder.layers_12.pre_mlp_layer_norm.scale.v/0 +0 -0
  8. checkpoint_1007000/target.decoder.layers_14.pre_self_attention_layer_norm.scale/.zarray +1 -0
  9. checkpoint_1007000/target.decoder.layers_14.pre_self_attention_layer_norm.scale/0 +0 -0
  10. checkpoint_1007000/target.decoder.layers_21.pre_mlp_layer_norm.scale/.zarray +1 -0
  11. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/.zarray +1 -0
  12. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/.zarray.__tmp11956591668185433077.~1663960300775166~ +1 -0
  13. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/.zarray.__tmp13516175280313004285.~1663960300421902~ +1 -0
  14. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/.zarray.__tmp13964544570706165907.~1663960300551182~ +1 -0
  15. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/.zarray.__tmp14796434722929521283.~1663960300889920~ +1 -0
  16. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/.zarray.__tmp5754672205082381332.~1663960300500509~ +1 -0
  17. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/.zarray.__tmp8753353903628498456.~1663960301025105~ +1 -0
  18. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/.zarray.__tmp9399295972313686183.~1663960300422872~ +1 -0
  19. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.0 +3 -0
  20. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.1 +3 -0
  21. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.2 +3 -0
  22. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.3 +3 -0
  23. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.4 +3 -0
  24. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.5 +3 -0
  25. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.6 +3 -0
  26. checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.7 +3 -0
  27. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/.zarray +1 -0
  28. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/.zarray.__tmp11044520425426663129.~1663960300775916~ +1 -0
  29. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/.zarray.__tmp11270147670760204708.~1663960300687158~ +1 -0
  30. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/.zarray.__tmp15745972426540854468.~1663960300496330~ +1 -0
  31. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/.zarray.__tmp18225983755576421068.~1663960300551492~ +1 -0
  32. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/.zarray.__tmp2925265231020371107.~1663960300887640~ +1 -0
  33. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/.zarray.__tmp8686227513087566420.~1663960300465579~ +1 -0
  34. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/.zarray.__tmp9539858247568583148.~1663960300500739~ +1 -0
  35. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/0.0 +3 -0
  36. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/1.0 +3 -0
  37. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/2.0 +3 -0
  38. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/3.0 +3 -0
  39. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/4.0 +3 -0
  40. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/5.0 +3 -0
  41. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/6.0 +3 -0
  42. checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/7.0 +3 -0
  43. checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/.zarray +1 -0
  44. checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/.zarray.__tmp10877149772695270707.~1663960300386835~ +1 -0
  45. checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/.zarray.__tmp13717016663163073878.~1663960300776452~ +1 -0
  46. checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/.zarray.__tmp14979235965970276431.~1663960300422071~ +1 -0
  47. checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/.zarray.__tmp15354932211873096836.~1663960300609171~ +1 -0
  48. checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/.zarray.__tmp7664672968798826125.~1663960300687845~ +1 -0
  49. checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/.zarray.__tmp7949530756955158107.~1663960300495220~ +1 -0
  50. checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.0 +3 -0
.gitattributes CHANGED
@@ -75,3 +75,50 @@ checkpoint_1007000/target.encoder.layers_2.mlp.wo.kernel/7.0 filter=lfs diff=lfs
75
  checkpoint_1007000/target.encoder.layers_2.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
76
  checkpoint_1007000/target.encoder.layers_2.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
77
  checkpoint_1007000/target.encoder.layers_2.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  checkpoint_1007000/target.encoder.layers_2.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
76
  checkpoint_1007000/target.encoder.layers_2.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
77
  checkpoint_1007000/target.encoder.layers_2.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
78
+ checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
79
+ checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
80
+ checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
81
+ checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
82
+ checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
83
+ checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
84
+ checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
85
+ checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
86
+ checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
87
+ checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
88
+ checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
89
+ checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
90
+ checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
91
+ checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
92
+ checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
93
+ checkpoint_1007000/target.encoder.layers_23.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
94
+ checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
95
+ checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
96
+ checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
97
+ checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
98
+ checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
99
+ checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
100
+ checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
101
+ checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
102
+ checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
103
+ checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
104
+ checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
105
+ checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
106
+ checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
107
+ checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
108
+ checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
109
+ checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
110
+ checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
111
+ checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
112
+ checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
113
+ checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
114
+ checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
115
+ checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
116
+ checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
117
+ checkpoint_1007000/target.encoder.layers_7.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
118
+ checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
119
+ checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
120
+ checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
121
+ checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
122
+ checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
123
+ checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
124
+ checkpoint_1007000/target.encoder.layers_4.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
checkpoint_1007000/state.param_states.decoder.layers_0.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_0.pre_self_attention_layer_norm.scale.v/0 ADDED
Binary file (15 kB). View file
 
checkpoint_1007000/state.param_states.decoder.layers_1.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_1.pre_cross_attention_layer_norm.scale.v/0 ADDED
Binary file (14.9 kB). View file
 
checkpoint_1007000/state.param_states.decoder.layers_12.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.decoder.layers_12.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (14.8 kB). View file
 
checkpoint_1007000/target.decoder.layers_14.pre_self_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_self_attention_layer_norm.scale/0 ADDED
Binary file (14.7 kB). View file
 
checkpoint_1007000/target.decoder.layers_21.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_21.self_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_21.self_attention.value.kernel/.zarray.__tmp11956591668185433077.~1663960300775166~ 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_21.self_attention.value.kernel/.zarray.__tmp13516175280313004285.~1663960300421902~ 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_21.self_attention.value.kernel/.zarray.__tmp13964544570706165907.~1663960300551182~ 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_21.self_attention.value.kernel/.zarray.__tmp14796434722929521283.~1663960300889920~ 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_21.self_attention.value.kernel/.zarray.__tmp5754672205082381332.~1663960300500509~ 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_21.self_attention.value.kernel/.zarray.__tmp8753353903628498456.~1663960301025105~ 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_21.self_attention.value.kernel/.zarray.__tmp9399295972313686183.~1663960300422872~ 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_21.self_attention.value.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b122e755dc83e4293b4a26e2f877082ae298d189646e6d0d339e1436a2774edf
3
+ size 7804386
checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4194bbd09e43afb7e844ae86b2fffa12b5c9cca26dc32cf1075283938e2f9577
3
+ size 7838351
checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d76e23a0dc7de0b60cea554cd84222fce20fca22300bbe1e64f8d34363ead5b
3
+ size 7827035
checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fdff26ac83319455eee3d7cd868c93b89252482804570ce867f690bac380ee3
3
+ size 7824922
checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d073412fa75dddad2776846dc7c540803893db430118080cdf6647d4e9148ec
3
+ size 7802387
checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8367b6a41ba831f9b50d1ba660919cf6989d1de1c918bc9816566062fead26bf
3
+ size 7804166
checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc608226863afd2f92c3312ce65085823cab55406ccded786b20389e585d67d3
3
+ size 7803903
checkpoint_1007000/target.decoder.layers_21.self_attention.value.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8e74dcae7fec8a0e19d12b9847c82a6421852db9cb9928a5d37d3b7afcbf7de
3
+ size 7803444
checkpoint_1007000/target.decoder.layers_22.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_22.mlp.wo.kernel/.zarray.__tmp11044520425426663129.~1663960300775916~ 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_22.mlp.wo.kernel/.zarray.__tmp11270147670760204708.~1663960300687158~ 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_22.mlp.wo.kernel/.zarray.__tmp15745972426540854468.~1663960300496330~ 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_22.mlp.wo.kernel/.zarray.__tmp18225983755576421068.~1663960300551492~ 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_22.mlp.wo.kernel/.zarray.__tmp2925265231020371107.~1663960300887640~ 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_22.mlp.wo.kernel/.zarray.__tmp8686227513087566420.~1663960300465579~ 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_22.mlp.wo.kernel/.zarray.__tmp9539858247568583148.~1663960300500739~ 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_22.mlp.wo.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6797e630e0688255ed3642418c2535ade87b92cf4bb2e17c8c85753eeb39dc14
3
+ size 19522519
checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647f2f72cd6556c6d528d6cb1625578c227e61511faeb6aa9703dacf0a50dd5b
3
+ size 19522715
checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad4e613b89d0ceb6a688375602766c8ab0e8a14f16849bfdfc6ebb24cd3ff772
3
+ size 19523035
checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c60565b7acd2b0cce01d3e0ff830fca410e134add7dc6a55ad62143bec57487b
3
+ size 19523112
checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f977061cffbd92a7e7157b5483f8c80208a6d73a223d3d176941bd0dabefe57e
3
+ size 19523634
checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba77d888ba9c3029adc2be2b822469ed48421c08242c12be6152733093bf9ed5
3
+ size 19522299
checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c1c872c300d660cd07c6914ace8e2969d48b1e9fdb9fad93b9e768ceb8ae3a
3
+ size 19522828
checkpoint_1007000/target.decoder.layers_22.mlp.wo.kernel/7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a787dc6543844e474a189be227258f9e5d197470438d92cc9e2517bd269f61ce
3
+ size 19523267
checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
checkpoint_1007000/target.encoder.layers_22.attention.key.kernel/.zarray.__tmp10877149772695270707.~1663960300386835~ 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_22.attention.key.kernel/.zarray.__tmp13717016663163073878.~1663960300776452~ 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_22.attention.key.kernel/.zarray.__tmp14979235965970276431.~1663960300422071~ 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_22.attention.key.kernel/.zarray.__tmp15354932211873096836.~1663960300609171~ 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_22.attention.key.kernel/.zarray.__tmp7664672968798826125.~1663960300687845~ 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_22.attention.key.kernel/.zarray.__tmp7949530756955158107.~1663960300495220~ 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_22.attention.key.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e30e2e94a7104c1b3882737f2bae56f06532944e8515a5b62657ada4ab7bba8
3
+ size 7798814