Hugging Face's logo

bigscience
/
mt0-t5x

Model card Files
xet
Community
TimeRobber commited on
Commit
8c8fd09
·
1 Parent(s): 51afe23

Upload part 38

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 +49 -0
  2. checkpoint_1007000/state.param_states.decoder.layers_10.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  3. checkpoint_1007000/state.param_states.decoder.layers_10.pre_mlp_layer_norm.scale.v/0 +0 -0
  4. checkpoint_1007000/state.param_states.decoder.layers_11.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
  5. checkpoint_1007000/state.param_states.decoder.layers_11.pre_cross_attention_layer_norm.scale.v/0 +0 -0
  6. checkpoint_1007000/state.param_states.encoder.layers_22.pre_attention_layer_norm.scale.v/.zarray +1 -0
  7. checkpoint_1007000/state.param_states.encoder.layers_22.pre_attention_layer_norm.scale.v/0 +0 -0
  8. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/.zarray +1 -0
  9. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/.zarray.__tmp10666301048271400128.~1663960300601872~ +1 -0
  10. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/.zarray.__tmp10824035044865767718.~1663960300467900~ +1 -0
  11. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/.zarray.__tmp17491665953918277627.~1663960300775137~ +1 -0
  12. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/.zarray.__tmp2698586933318194643.~1663960300493108~ +1 -0
  13. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/.zarray.__tmp3063477194367769089.~1663960300728221~ +1 -0
  14. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/.zarray.__tmp3629286470904913908.~1663960300685961~ +1 -0
  15. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/.zarray.__tmp5154167650306256182.~1663960300499769~ +1 -0
  16. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.0 +3 -0
  17. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.1 +3 -0
  18. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.2 +3 -0
  19. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.3 +3 -0
  20. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.4 +3 -0
  21. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.5 +3 -0
  22. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.6 +3 -0
  23. checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.7 +3 -0
  24. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/.zarray +1 -0
  25. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/.zarray.__tmp12292122855751842815.~1663960300886463~ +1 -0
  26. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/.zarray.__tmp12729170680231462171.~1663960300775671~ +1 -0
  27. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/.zarray.__tmp16288759272656539980.~1663960300622392~ +1 -0
  28. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/.zarray.__tmp2097918179125387591.~1663960300471042~ +1 -0
  29. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/.zarray.__tmp27539476875501871.~1663960300685425~ +1 -0
  30. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/.zarray.__tmp3982320326126219065.~1663960300498267~ +1 -0
  31. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/.zarray.__tmp4583192192703197948.~1663960300627170~ +1 -0
  32. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.0 +3 -0
  33. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.1 +3 -0
  34. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.2 +3 -0
  35. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.3 +3 -0
  36. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.4 +3 -0
  37. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.5 +3 -0
  38. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.6 +3 -0
  39. checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.7 +3 -0
  40. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/.zarray +1 -0
  41. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/.zarray.__tmp10521466314548349909.~1663960300623733~ +1 -0
  42. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/.zarray.__tmp1268806510747428351.~1663960300776988~ +1 -0
  43. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/.zarray.__tmp5157424613732213906.~1663960301026243~ +1 -0
  44. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/.zarray.__tmp6307815978816431402.~1663960300500621~ +1 -0
  45. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/.zarray.__tmp7128591363366176481.~1663960300865877~ +1 -0
  46. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/.zarray.__tmp7446400039440086678.~1663960300687825~ +1 -0
  47. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/.zarray.__tmp7547867216114642093.~1663960300891116~ +1 -0
  48. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/0.0 +3 -0
  49. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/1.0 +3 -0
  50. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/2.0 +3 -0
.gitattributes CHANGED
@@ -1941,3 +1941,52 @@ checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.key.kernel
1941
  checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
1942
  checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
1943
  checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1941
  checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
1942
  checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
1943
  checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
1944
+ checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1945
+ checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
1946
+ checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
1947
+ checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
1948
+ checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
1949
+ checkpoint_1007000/target.decoder.layers_7.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
1950
+ checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
1951
+ checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
1952
+ checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1953
+ checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
1954
+ checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
1955
+ checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
1956
+ checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
1957
+ checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
1958
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
1959
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
1960
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
1961
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1962
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
1963
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
1964
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
1965
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
1966
+ checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
1967
+ checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
1968
+ checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
1969
+ checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1970
+ checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
1971
+ checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
1972
+ checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
1973
+ checkpoint_1007000/target.encoder.layers_17.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
1974
+ checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
1975
+ checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
1976
+ checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1977
+ checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
1978
+ checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
1979
+ checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
1980
+ checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
1981
+ checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
1982
+ checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
1983
+ checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
1984
+ checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
1985
+ checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1986
+ checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
1987
+ checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
1988
+ checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
1989
+ checkpoint_1007000/target.decoder.layers_9.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
1990
+ checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
1991
+ checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
1992
+ checkpoint_1007000/target.encoder.layers_2.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoint_1007000/state.param_states.decoder.layers_10.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_10.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (14.7 kB). View file
 
checkpoint_1007000/state.param_states.decoder.layers_11.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_11.pre_cross_attention_layer_norm.scale.v/0 ADDED
Binary file (14.8 kB). View file
 
checkpoint_1007000/state.param_states.encoder.layers_22.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_22.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (14.7 kB). View file
 
checkpoint_1007000/target.decoder.layers_12.encoder_decoder_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.decoder.layers_12.encoder_decoder_attention.key.kernel/.zarray.__tmp10666301048271400128.~1663960300601872~ 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_12.encoder_decoder_attention.key.kernel/.zarray.__tmp10824035044865767718.~1663960300467900~ 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_12.encoder_decoder_attention.key.kernel/.zarray.__tmp17491665953918277627.~1663960300775137~ 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_12.encoder_decoder_attention.key.kernel/.zarray.__tmp2698586933318194643.~1663960300493108~ 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_12.encoder_decoder_attention.key.kernel/.zarray.__tmp3063477194367769089.~1663960300728221~ 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_12.encoder_decoder_attention.key.kernel/.zarray.__tmp3629286470904913908.~1663960300685961~ 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_12.encoder_decoder_attention.key.kernel/.zarray.__tmp5154167650306256182.~1663960300499769~ 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_12.encoder_decoder_attention.key.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:032375b7f17b22d771bd0020429fa616e224566883048698b82fd3b42e509427
3
+ size 7812332
checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68f0450f185321f03b135f8ff09246f3f7ec1816ce112761991cc48b8fda3e8c
3
+ size 7812660
checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:291c660532e38959ff70eb206b6d27fa4da2b2cf6fa8c4e436b81f5bddaf1617
3
+ size 7809139
checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdba720983884ce8405ad6ce311c5d853b35e8a3b5a4a72027c818f66f669f02
3
+ size 7810129
checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72ba2c6261edbb62277ba045a91c28b20fef9ffc4b50e84534cbb158419a64b2
3
+ size 7810466
checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a74663521ab7b3ecc10255c186ae1d14ad14e96826a4db34e14fb86c47d57ad
3
+ size 7814949
checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e3d94c7ec301f6390077762054354c0fcfd0e64d226d2c89fcb74e4ed6677e
3
+ size 7808788
checkpoint_1007000/target.decoder.layers_12.encoder_decoder_attention.key.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7ae4715414d9737cc9fa3a13221d8a6dd9a41d1cc86ce0f7e11d198e2aa96c0
3
+ size 7815597
checkpoint_1007000/target.decoder.layers_20.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_20.self_attention.value.kernel/.zarray.__tmp12292122855751842815.~1663960300886463~ 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_20.self_attention.value.kernel/.zarray.__tmp12729170680231462171.~1663960300775671~ 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_20.self_attention.value.kernel/.zarray.__tmp16288759272656539980.~1663960300622392~ 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_20.self_attention.value.kernel/.zarray.__tmp2097918179125387591.~1663960300471042~ 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_20.self_attention.value.kernel/.zarray.__tmp27539476875501871.~1663960300685425~ 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_20.self_attention.value.kernel/.zarray.__tmp3982320326126219065.~1663960300498267~ 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_20.self_attention.value.kernel/.zarray.__tmp4583192192703197948.~1663960300627170~ 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_20.self_attention.value.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e568963ea246fa4c96d9507370641c8b05c3f2b1ccae7c891f0ee063cc997c
3
+ size 7824823
checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3f1f3a96ad7c6a1331e850a7c197b91bb73b9af629e38437170681d61b0f828
3
+ size 7817700
checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67fabd789ec771df19421123c323a2f6e1cc2c61607759f43e5f66b2b53224ed
3
+ size 7819162
checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44375ccd546fbe9522b4ca02179b58ba2cf1e174954c3c74ea7b7f6ad87b3814
3
+ size 7806485
checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c735eece22368768f537e6cbb51bfb6dcac3820ac98d552f11d3653d7ab8b4c3
3
+ size 7841992
checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a57bea9076d1b273248ede820670f20906fcc891448ad05e45ca66af2a97a3e
3
+ size 7806791
checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51870d868570ba8c0f9fe8925511883f27038c43b9e30d235a915750630b6814
3
+ size 7837160
checkpoint_1007000/target.decoder.layers_20.self_attention.value.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05cb07201e1921a2ea5b8a2565defc464f8ff5b54e43fd3e4182b848f4026922
3
+ size 7807011
checkpoint_1007000/target.decoder.layers_23.encoder_decoder_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_23.encoder_decoder_attention.out.kernel/.zarray.__tmp10521466314548349909.~1663960300623733~ 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_23.encoder_decoder_attention.out.kernel/.zarray.__tmp1268806510747428351.~1663960300776988~ 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_23.encoder_decoder_attention.out.kernel/.zarray.__tmp5157424613732213906.~1663960301026243~ 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_23.encoder_decoder_attention.out.kernel/.zarray.__tmp6307815978816431402.~1663960300500621~ 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_23.encoder_decoder_attention.out.kernel/.zarray.__tmp7128591363366176481.~1663960300865877~ 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_23.encoder_decoder_attention.out.kernel/.zarray.__tmp7446400039440086678.~1663960300687825~ 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_23.encoder_decoder_attention.out.kernel/.zarray.__tmp7547867216114642093.~1663960300891116~ 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_23.encoder_decoder_attention.out.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:896ef7c9ecff55837ea9d4c8216749900b5cc1ed23413c6bac17e2ba3a6ba16e
3
+ size 7799623
checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581c455bbebe40adcc8ece3e4fe2417feb72fa96535b23071f5584a891f544e7
3
+ size 7801952
checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.out.kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b93228b4bffddaee05d244ad6e987ddf7895ab8f7d77a16ab335afebc63aae3
3
+ size 7803410