Hugging Face's logo

bigscience
/
mt0-t5x

Model card Files
xet
Community
TimeRobber commited on
Commit
824ee4f
·
1 Parent(s): 0b42be6

Upload part 63

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 +41 -0
  2. checkpoint_1007000/state.param_states.decoder.layers_15.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
  3. checkpoint_1007000/state.param_states.decoder.layers_15.pre_self_attention_layer_norm.scale.v/0 +0 -0
  4. checkpoint_1007000/state.param_states.decoder.layers_4.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
  5. checkpoint_1007000/state.param_states.decoder.layers_4.pre_self_attention_layer_norm.scale.v/0 +0 -0
  6. checkpoint_1007000/state.param_states.encoder.layers_17.pre_attention_layer_norm.scale.v/.zarray +1 -0
  7. checkpoint_1007000/state.param_states.encoder.layers_17.pre_attention_layer_norm.scale.v/0 +0 -0
  8. checkpoint_1007000/state.param_states.encoder.layers_22.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  9. checkpoint_1007000/state.param_states.encoder.layers_22.pre_mlp_layer_norm.scale.v/0 +0 -0
  10. checkpoint_1007000/state.param_states.encoder.layers_7.pre_attention_layer_norm.scale.v/.zarray +1 -0
  11. checkpoint_1007000/state.param_states.encoder.layers_7.pre_attention_layer_norm.scale.v/0 +0 -0
  12. checkpoint_1007000/target.decoder.layers_14.pre_mlp_layer_norm.scale/.zarray +1 -0
  13. checkpoint_1007000/target.decoder.layers_14.pre_mlp_layer_norm.scale/0 +0 -0
  14. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/.zarray +1 -0
  15. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/.zarray.__tmp11022920270577004350.~1663960300774422~ +1 -0
  16. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/.zarray.__tmp12220587027976758189.~1663960300497318~ +1 -0
  17. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/.zarray.__tmp15139372564952119141.~1663960300686732~ +1 -0
  18. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/.zarray.__tmp16578100984275369226.~1663960300312261~ +1 -0
  19. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/.zarray.__tmp17480015849416176736.~1663960300497624~ +1 -0
  20. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/.zarray.__tmp2511551157182493797.~1663960300425453~ +1 -0
  21. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/.zarray.__tmp4921498194718520503.~1663960300778506~ +1 -0
  22. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.0 +3 -0
  23. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.1 +3 -0
  24. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.2 +3 -0
  25. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.3 +3 -0
  26. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.4 +3 -0
  27. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.5 +3 -0
  28. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.6 +3 -0
  29. checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.7 +3 -0
  30. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/.zarray +1 -0
  31. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/.zarray.__tmp13271049767305026386.~1663960300421875~ +1 -0
  32. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/.zarray.__tmp13980530611791975235.~1663960300386392~ +1 -0
  33. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/.zarray.__tmp17204175130635238953.~1663960300501645~ +1 -0
  34. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/.zarray.__tmp17438993676552112525.~1663960300777299~ +1 -0
  35. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/.zarray.__tmp17719064599151580694.~1663960301029565~ +1 -0
  36. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/.zarray.__tmp1896017102952188623.~1663960300546485~ +1 -0
  37. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/.zarray.__tmp2827239177966120361.~1663960300347528~ +1 -0
  38. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.0 +3 -0
  39. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.1 +3 -0
  40. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.2 +3 -0
  41. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.3 +3 -0
  42. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.4 +3 -0
  43. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.5 +3 -0
  44. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.6 +3 -0
  45. checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.7 +3 -0
  46. checkpoint_1007000/target.decoder.layers_22.pre_mlp_layer_norm.scale/.zarray +1 -0
  47. checkpoint_1007000/target.decoder.layers_22.pre_mlp_layer_norm.scale/0 +0 -0
  48. checkpoint_1007000/target.decoder.layers_4.pre_cross_attention_layer_norm.scale/.zarray +1 -0
  49. checkpoint_1007000/target.decoder.layers_4.pre_cross_attention_layer_norm.scale/0 +0 -0
  50. checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/.zarray +1 -0
.gitattributes CHANGED
@@ -3146,3 +3146,44 @@ checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.6 filter=lfs
3146
  checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3147
  checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3148
  checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3146
  checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3147
  checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3148
  checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3149
+ checkpoint_1007000/target.encoder.layers_3.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
3150
+ checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
3151
+ checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
3152
+ checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3153
+ checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
3154
+ checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3155
+ checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3156
+ checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3157
+ checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
3158
+ checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
3159
+ checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
3160
+ checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3161
+ checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
3162
+ checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3163
+ checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3164
+ checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3165
+ checkpoint_1007000/target.encoder.layers_2.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
3166
+ checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
3167
+ checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
3168
+ checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3169
+ checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
3170
+ checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3171
+ checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3172
+ checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3173
+ checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
3174
+ checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
3175
+ checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
3176
+ checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3177
+ checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
3178
+ checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3179
+ checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3180
+ checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3181
+ checkpoint_1007000/target.decoder.layers_9.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
3182
+ checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
3183
+ checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
3184
+ checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
3185
+ checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
3186
+ checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
3187
+ checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
3188
+ checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
3189
+ checkpoint_1007000/target.encoder.layers_6.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
checkpoint_1007000/state.param_states.decoder.layers_15.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_15.pre_self_attention_layer_norm.scale.v/0 ADDED
Binary file (15.1 kB). View file
 
checkpoint_1007000/state.param_states.decoder.layers_4.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_4.pre_self_attention_layer_norm.scale.v/0 ADDED
Binary file (15 kB). View file
 
checkpoint_1007000/state.param_states.encoder.layers_17.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_17.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (15.1 kB). View file
 
checkpoint_1007000/state.param_states.encoder.layers_22.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_22.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (14.7 kB). View file
 
checkpoint_1007000/state.param_states.encoder.layers_7.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_7.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (15.3 kB). View file
 
checkpoint_1007000/target.decoder.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.decoder.layers_14.pre_mlp_layer_norm.scale/0 ADDED
Binary file (14.5 kB). View file
 
checkpoint_1007000/target.decoder.layers_14.self_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.self_attention.query.kernel/.zarray.__tmp11022920270577004350.~1663960300774422~ 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.self_attention.query.kernel/.zarray.__tmp12220587027976758189.~1663960300497318~ 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.self_attention.query.kernel/.zarray.__tmp15139372564952119141.~1663960300686732~ 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.self_attention.query.kernel/.zarray.__tmp16578100984275369226.~1663960300312261~ 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.self_attention.query.kernel/.zarray.__tmp17480015849416176736.~1663960300497624~ 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.self_attention.query.kernel/.zarray.__tmp2511551157182493797.~1663960300425453~ 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.self_attention.query.kernel/.zarray.__tmp4921498194718520503.~1663960300778506~ 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.self_attention.query.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4ab797db4479c756877d210b45c3558631ae610b24f4a045e83b41739b846b0
3
+ size 7801899
checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9814d5f1a87fc0ec2832ab878707b7ec77731a762aa65396a99b972b47fe7019
3
+ size 7826659
checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a89494d51e067e07809d27123f0aebd13d78e695235f001e0e420093c6699e5
3
+ size 7807628
checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:368e5949f5334c962047f9e6468ad54ffa64cdd1ce4480c65bece08576882eb1
3
+ size 7805853
checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:864ce3cdf3901157ac3db33d083476bf94b768630c49313ccbc53f58e886e3c8
3
+ size 7804627
checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581a820bdbba0cf22fcf9b503914270678cf77445dde99a96e1efd478e9df5ae
3
+ size 7809132
checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a33a40af53889b822127b3d2d85c6c1f0f8d0de3816cd8e5e0c6a95f566a6bda
3
+ size 7808035
checkpoint_1007000/target.decoder.layers_14.self_attention.query.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b85d7b0213b0c43aa789d85c0bbddeb8aa51b06c2a4670247bd7778d7ef7b66b
3
+ size 7800864
checkpoint_1007000/target.decoder.layers_15.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_15.encoder_decoder_attention.value.kernel/.zarray.__tmp13271049767305026386.~1663960300421875~ 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_15.encoder_decoder_attention.value.kernel/.zarray.__tmp13980530611791975235.~1663960300386392~ 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_15.encoder_decoder_attention.value.kernel/.zarray.__tmp17204175130635238953.~1663960300501645~ 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_15.encoder_decoder_attention.value.kernel/.zarray.__tmp17438993676552112525.~1663960300777299~ 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_15.encoder_decoder_attention.value.kernel/.zarray.__tmp17719064599151580694.~1663960301029565~ 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_15.encoder_decoder_attention.value.kernel/.zarray.__tmp1896017102952188623.~1663960300546485~ 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_15.encoder_decoder_attention.value.kernel/.zarray.__tmp2827239177966120361.~1663960300347528~ 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_15.encoder_decoder_attention.value.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d40aedeec5c2435a0ca948ffddf06313ce097d1cae3928169e8a1da344a862dd
3
+ size 7815923
checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:379ddfec3ec95ac675770a88f4375d6f4a8d84aef1c5819295c9e463e5671293
3
+ size 7812563
checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c68b02fe9307a1f98af82b7484f9f7774cc16df390f1042b036c5a8ebb452e
3
+ size 7812960
checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:481aab06ec959d8c2f10d75eef74002b703c9ebfe62b3a5d80906654df627db0
3
+ size 7811120
checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef9b8074c9cbb4079ee86a4654a5970238e6ee597b5ef31c4b5019a405188a3f
3
+ size 7815297
checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:649134599f02266c64bc56c281dd14d73035e7599ffad5cb01f3df8033017d9d
3
+ size 7813692
checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80abb5910f212bb1f5dac6d6d9d67753086f0cabb34c837d599527c40b49ad84
3
+ size 7815537
checkpoint_1007000/target.decoder.layers_15.encoder_decoder_attention.value.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5d005fbcb2ba4595dc6eac506b2ceadfbe10e03ab8795596facc299de6bfbcb
3
+ size 7816153
checkpoint_1007000/target.decoder.layers_22.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_22.pre_mlp_layer_norm.scale/0 ADDED
Binary file (13.8 kB). View file
 
checkpoint_1007000/target.decoder.layers_4.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_4.pre_cross_attention_layer_norm.scale/0 ADDED
Binary file (14.9 kB). View file
 
checkpoint_1007000/target.decoder.layers_9.self_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}