Hugging Face's logo

bigscience
/
mt0-t5x

Model card Files
xet
Community
TimeRobber commited on
Commit
e42c1df
·
1 Parent(s): 651860e

Upload part 44

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 +50 -0
  2. checkpoint_1007000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
  3. checkpoint_1007000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/0 +0 -0
  4. checkpoint_1007000/state.param_states.decoder.layers_21.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
  5. checkpoint_1007000/state.param_states.decoder.layers_21.pre_cross_attention_layer_norm.scale.v/0 +0 -0
  6. checkpoint_1007000/state.param_states.encoder.layers_12.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  7. checkpoint_1007000/state.param_states.encoder.layers_12.pre_mlp_layer_norm.scale.v/0 +0 -0
  8. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/.zarray +1 -0
  9. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/.zarray.__tmp13317862693414254449.~1663960300266463~ +1 -0
  10. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/.zarray.__tmp18351130551550344796.~1663960300986535~ +1 -0
  11. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/.zarray.__tmp282961741546003797.~1663960300014359~ +1 -0
  12. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/.zarray.__tmp3981875622317747831.~1663960300134002~ +1 -0
  13. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/.zarray.__tmp9770001286954173129.~1663960300268068~ +1 -0
  14. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/0.0 +3 -0
  15. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/1.0 +3 -0
  16. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/2.0 +3 -0
  17. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/3.0 +3 -0
  18. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/4.0 +3 -0
  19. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/5.0 +3 -0
  20. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/6.0 +3 -0
  21. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/7.0 +3 -0
  22. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/.zarray +1 -0
  23. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/.zarray.__tmp14755775162671015479.~1663960300313196~ +1 -0
  24. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/.zarray.__tmp15929711136369962275.~1663960300466126~ +1 -0
  25. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/.zarray.__tmp3211724514550199944.~1663960300686406~ +1 -0
  26. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/.zarray.__tmp5542698970820471895.~1663960300504670~ +1 -0
  27. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/.zarray.__tmp5757567167324112445.~1663960300775434~ +1 -0
  28. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/.zarray.__tmp9536086688303990048.~1663960300420628~ +1 -0
  29. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/.zarray.__tmp9613167283394802845.~1663960300622402~ +1 -0
  30. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.0 +3 -0
  31. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.1 +3 -0
  32. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.2 +3 -0
  33. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.3 +3 -0
  34. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.4 +3 -0
  35. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.5 +3 -0
  36. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.6 +3 -0
  37. checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.7 +3 -0
  38. checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/.zarray +1 -0
  39. checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/.zarray.__tmp13557785600670434127.~1663960300070675~ +1 -0
  40. checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/.zarray.__tmp3142583028134086573.~1663960300087867~ +1 -0
  41. checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.0 +3 -0
  42. checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.1 +3 -0
  43. checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.2 +3 -0
  44. checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.3 +3 -0
  45. checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.4 +3 -0
  46. checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.5 +3 -0
  47. checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.6 +3 -0
  48. checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.7 +3 -0
  49. checkpoint_1007000/target.encoder.layers_12.mlp.wi_0.kernel/.zarray +1 -0
  50. checkpoint_1007000/target.encoder.layers_12.mlp.wi_0.kernel/.zarray.__tmp14933477324427723908.~1663960300554232~ +1 -0
.gitattributes CHANGED
@@ -2237,3 +2237,53 @@ checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.2 filter=lfs
2237
  checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2238
  checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2239
  checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2237
  checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2238
  checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2239
  checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2240
+ checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2241
+ checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2242
+ checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2243
+ checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2244
+ checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2245
+ checkpoint_1007000/target.encoder.layers_22.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2246
+ checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2247
+ checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2248
+ checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2249
+ checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2250
+ checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2251
+ checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2252
+ checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2253
+ checkpoint_1007000/target.encoder.layers_8.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2254
+ checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2255
+ checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2256
+ checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2257
+ checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2258
+ checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2259
+ checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2260
+ checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2261
+ checkpoint_1007000/target.encoder.layers_9.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2262
+ checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2263
+ checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2264
+ checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2265
+ checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2266
+ checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2267
+ checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2268
+ checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2269
+ checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2270
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
2271
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
2272
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
2273
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2274
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
2275
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
2276
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
2277
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
2278
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2279
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2280
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2281
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2282
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2283
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2284
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2285
+ checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2286
+ checkpoint_1007000/target.encoder.layers_12.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2287
+ checkpoint_1007000/target.encoder.layers_12.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2288
+ checkpoint_1007000/target.encoder.layers_12.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2289
+ checkpoint_1007000/target.encoder.layers_12.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
checkpoint_1007000/state.param_states.decoder.layers_0.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_0.pre_cross_attention_layer_norm.scale.v/0 ADDED
Binary file (14.9 kB). View file
 
checkpoint_1007000/state.param_states.decoder.layers_21.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_21.pre_cross_attention_layer_norm.scale.v/0 ADDED
Binary file (14.4 kB). View file
 
checkpoint_1007000/state.param_states.encoder.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.encoder.layers_12.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (15.3 kB). View file
 
checkpoint_1007000/target.decoder.layers_11.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_11.encoder_decoder_attention.out.kernel/.zarray.__tmp13317862693414254449.~1663960300266463~ 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_11.encoder_decoder_attention.out.kernel/.zarray.__tmp18351130551550344796.~1663960300986535~ 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_11.encoder_decoder_attention.out.kernel/.zarray.__tmp282961741546003797.~1663960300014359~ 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_11.encoder_decoder_attention.out.kernel/.zarray.__tmp3981875622317747831.~1663960300134002~ 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_11.encoder_decoder_attention.out.kernel/.zarray.__tmp9770001286954173129.~1663960300268068~ 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_11.encoder_decoder_attention.out.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7960fb893fe2dac92b7fa93a0bb80569a87a012d3951145a9f778fe34cf4ee2d
3
+ size 7817722
checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824b26e4bccfc6a5e1ebc0e3cacaf8695057509a6fff8d2214ba70ac11d3e7c5
3
+ size 7817686
checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4634c7a1e6a40b31ccbe1ef9485a2330341d6956098240b4871f3b11c5119779
3
+ size 7818607
checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf8b8656b9b62fc00f8c0c3732fcef73b33d1ec34f11c72be713ce4c438a201a
3
+ size 7819206
checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c491e23dd2865b7a66b7e06b8c046c66ac3c5edcbb8cc784090b3f4f2eb635cb
3
+ size 7817334
checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47ccce5b4f0a7fbfa2c6d6a847cff8a3df46d89110154ea38ccc428e9b6f05be
3
+ size 7817902
checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:805e10892b9a692b20413f4f1dc3d854d255547037c99253dc2781367403a4e1
3
+ size 7818753
checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.out.kernel/7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eea6a1e47981f1f2afee929609ae82d10f0b5f743c6759b9a125d6c9e4656ea0
3
+ size 7817893
checkpoint_1007000/target.decoder.layers_23.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_23.encoder_decoder_attention.key.kernel/.zarray.__tmp14755775162671015479.~1663960300313196~ 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_23.encoder_decoder_attention.key.kernel/.zarray.__tmp15929711136369962275.~1663960300466126~ 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_23.encoder_decoder_attention.key.kernel/.zarray.__tmp3211724514550199944.~1663960300686406~ 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_23.encoder_decoder_attention.key.kernel/.zarray.__tmp5542698970820471895.~1663960300504670~ 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_23.encoder_decoder_attention.key.kernel/.zarray.__tmp5757567167324112445.~1663960300775434~ 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_23.encoder_decoder_attention.key.kernel/.zarray.__tmp9536086688303990048.~1663960300420628~ 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_23.encoder_decoder_attention.key.kernel/.zarray.__tmp9613167283394802845.~1663960300622402~ 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_23.encoder_decoder_attention.key.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12ce1381cf2febf93d6a7ec9bbb6be4b0c6a9877c55515f20fa48d3b47de5312
3
+ size 7803437
checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ceb3a689397ed013780b08c7e82f4883eb5709491d111a5f07087c0db4faf1
3
+ size 7804047
checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d58c3ef1bba3427b79468a212b805f67ff973ae7396fd09002a22af391db0ad8
3
+ size 7809740
checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:627d2237fd256e19ad540b450568ea5b17d3e0a81f41ec8c0f5073688f55d04d
3
+ size 7803345
checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9915e5c6769013b943753c4a23e3e57abb129bf485bbf7befc79852453b0d03e
3
+ size 7807705
checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7d7ac10eae42c145a13ca94d6dfdfc81e1a65defaa39396076b6756413cfc21
3
+ size 7807067
checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9c4f6bb9ebdb65388a93610d2382fb2bb8248defc2891f4b1c733176124775
3
+ size 7806649
checkpoint_1007000/target.decoder.layers_23.encoder_decoder_attention.key.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:206703a0a9d6b238ae3bb06fdf454d211f4e884102ea276c0b767c96d5b34090
3
+ size 7809570
checkpoint_1007000/target.encoder.layers_12.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.encoder.layers_12.attention.value.kernel/.zarray.__tmp13557785600670434127.~1663960300070675~ 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_12.attention.value.kernel/.zarray.__tmp3142583028134086573.~1663960300087867~ 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_12.attention.value.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01cdf0f52ebef390dc39091c67ecdb37c98b22bb857984b348e799930a8e4f43
3
+ size 7807700
checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da550d68a3c851242c291656346254965590577ae5b415ef0c111fa2b82833d
3
+ size 7805692
checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a337032e72b0d809f9086488a864528e75cce7047dcf905a457ab00aa9287cb7
3
+ size 7804683
checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b8d64803d550be3a79f46ce1004a7d585a63453cd3723cf39f33748ac99c72
3
+ size 7803862
checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e89405738cc9fb550a4e026dcd02371fba2e193bf82b7c80510bcd2bb0565576
3
+ size 7804358
checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ced267946938aa9c1c23c83afbdc583da75e71a00ac4b18be10ae790ad0d326
3
+ size 7806170
checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b4dcfa0b03c0e2fd3bf9f8d831804b07775835dab08a0b98be808ac4c80cd6
3
+ size 7808337
checkpoint_1007000/target.encoder.layers_12.attention.value.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cbb6d12a558b827cf7f37aafb3ed797b43bcd394b31c0dbcbbd58f6de8dae43
3
+ size 7807169
checkpoint_1007000/target.encoder.layers_12.mlp.wi_0.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.encoder.layers_12.mlp.wi_0.kernel/.zarray.__tmp14933477324427723908.~1663960300554232~ 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}