Hugging Face's logo

bigscience
/
mt0-t5x

Model card Files
xet
Community
TimeRobber commited on
Commit
4fa7516
·
1 Parent(s): fec22c9

Upload part 24

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 +46 -0
  2. checkpoint_1007000/state.param_states.decoder.layers_5.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
  3. checkpoint_1007000/state.param_states.decoder.layers_5.pre_self_attention_layer_norm.scale.v/0 +0 -0
  4. checkpoint_1007000/target.decoder.layers_0.pre_cross_attention_layer_norm.scale/.zarray +1 -0
  5. checkpoint_1007000/target.decoder.layers_0.pre_cross_attention_layer_norm.scale/0 +0 -0
  6. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/.zarray +1 -0
  7. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/.zarray.__tmp10095019869978437800.~1663960300271896~ +1 -0
  8. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/.zarray.__tmp1615446246831715646.~1663960299886586~ +1 -0
  9. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/.zarray.__tmp16375465021480986488.~1663960300068936~ +1 -0
  10. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/.zarray.__tmp5534222237786118969.~1663960300221867~ +1 -0
  11. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/.zarray.__tmp8420835577685355328.~1663960299771904~ +1 -0
  12. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.0 +3 -0
  13. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.1 +3 -0
  14. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.2 +3 -0
  15. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.3 +3 -0
  16. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.4 +3 -0
  17. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.5 +3 -0
  18. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.6 +3 -0
  19. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.7 +3 -0
  20. checkpoint_1007000/target.decoder.layers_10.mlp.wi_1.kernel/0.1 +3 -0
  21. checkpoint_1007000/target.decoder.layers_10.mlp.wi_1.kernel/0.7 +3 -0
  22. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/.zarray +1 -0
  23. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/.zarray.__tmp1284481477073725886.~1663960300551089~ +1 -0
  24. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/.zarray.__tmp13030154618658172265.~1663960300421589~ +1 -0
  25. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/.zarray.__tmp13061122469800148957.~1663960300873570~ +1 -0
  26. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/.zarray.__tmp13391909884930776585.~1663960300421563~ +1 -0
  27. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/.zarray.__tmp2880886554391784844.~1663960300780176~ +1 -0
  28. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/.zarray.__tmp3361864013994727667.~1663960300602674~ +1 -0
  29. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/.zarray.__tmp6305757313857656718.~1663960300683740~ +1 -0
  30. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.0 +3 -0
  31. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.1 +3 -0
  32. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.2 +3 -0
  33. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.3 +3 -0
  34. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.4 +3 -0
  35. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.5 +3 -0
  36. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.6 +3 -0
  37. checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.7 +3 -0
  38. checkpoint_1007000/target.decoder.layers_15.pre_self_attention_layer_norm.scale/.zarray +1 -0
  39. checkpoint_1007000/target.decoder.layers_15.pre_self_attention_layer_norm.scale/0 +0 -0
  40. checkpoint_1007000/target.decoder.layers_17.pre_cross_attention_layer_norm.scale/.zarray +1 -0
  41. checkpoint_1007000/target.decoder.layers_17.pre_cross_attention_layer_norm.scale/0 +0 -0
  42. checkpoint_1007000/target.decoder.layers_19.pre_self_attention_layer_norm.scale/.zarray +1 -0
  43. checkpoint_1007000/target.decoder.layers_19.pre_self_attention_layer_norm.scale/0 +0 -0
  44. checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/.zarray +1 -0
  45. checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/.zarray.__tmp10498699521731813312.~1663960300989010~ +1 -0
  46. checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/.zarray.__tmp17907976336290164547.~1663960300548811~ +1 -0
  47. checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/.zarray.__tmp2275540253024918713.~1663960300987387~ +1 -0
  48. checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/.zarray.__tmp3308913374843981282.~1663960300599989~ +1 -0
  49. checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/.zarray.__tmp8132968568760133378.~1663960300688721~ +1 -0
  50. checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/2.0 +3 -0
.gitattributes CHANGED
@@ -1247,3 +1247,49 @@ checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/6.0 filter
1247
  checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
1248
  checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
1249
  checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1247
  checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
1248
  checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
1249
  checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1250
+ checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
1251
+ checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
1252
+ checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
1253
+ checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
1254
+ checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
1255
+ checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
1256
+ checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1257
+ checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
1258
+ checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
1259
+ checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
1260
+ checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
1261
+ checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
1262
+ checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
1263
+ checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
1264
+ checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
1265
+ checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1266
+ checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
1267
+ checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
1268
+ checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
1269
+ checkpoint_1007000/target.encoder.layers_4.attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
1270
+ checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
1271
+ checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
1272
+ checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1273
+ checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
1274
+ checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
1275
+ checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
1276
+ checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
1277
+ checkpoint_1007000/target.encoder.layers_11.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
1278
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
1279
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
1280
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1281
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
1282
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
1283
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
1284
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
1285
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
1286
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
1287
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
1288
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
1289
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
1290
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
1291
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
1292
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
1293
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
1294
+ checkpoint_1007000/target.decoder.layers_10.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
1295
+ checkpoint_1007000/target.decoder.layers_10.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
checkpoint_1007000/state.param_states.decoder.layers_5.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_5.pre_self_attention_layer_norm.scale.v/0 ADDED
Binary file (15 kB). View file
 
checkpoint_1007000/target.decoder.layers_0.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_0.pre_cross_attention_layer_norm.scale/0 ADDED
Binary file (14.8 kB). View file
 
checkpoint_1007000/target.decoder.layers_10.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_10.encoder_decoder_attention.value.kernel/.zarray.__tmp10095019869978437800.~1663960300271896~ 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_10.encoder_decoder_attention.value.kernel/.zarray.__tmp1615446246831715646.~1663960299886586~ 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_10.encoder_decoder_attention.value.kernel/.zarray.__tmp16375465021480986488.~1663960300068936~ 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_10.encoder_decoder_attention.value.kernel/.zarray.__tmp5534222237786118969.~1663960300221867~ 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_10.encoder_decoder_attention.value.kernel/.zarray.__tmp8420835577685355328.~1663960299771904~ 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_10.encoder_decoder_attention.value.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d7dc066882499e437e095fc7b0157f48b0ace257648c1957e3121bf6ccba1ea
3
+ size 7803768
checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b7db396d0b3b9df3c450cc1fa005ac460e4e7fc4fdeb39b249bdc0d924ae5f0
3
+ size 7804130
checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6f88d9b74a81937b20c5f672a19542d04b58bd80d4e5e861f1b0ab8dbe567a5
3
+ size 7805419
checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37b043aa2eb620e5645e94120c0af702c7c8a6672043dfcf1b1352a27138863c
3
+ size 7808813
checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cb8f9dd2b0027a5177227ac41df3fbfd1a692477c4a23166bca01131c9d7c41
3
+ size 7807867
checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f258812bf91edbddb4add341382de32b048a3af93b346dd26e871c7423253926
3
+ size 7806447
checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d61c54e8901ec7d0b49e8d27161f472c7df654169c7f1c5eba9e84f74a1a7230
3
+ size 7809445
checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.value.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b872b2daa334b78517e68b0e89667119fdbadbd507d27f34a80bf4f1915b7327
3
+ size 7802860
checkpoint_1007000/target.decoder.layers_10.mlp.wi_1.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81ff6e7e319efab925e85952c96e57e334d5bec6be6006742f5c81d0ad04b62d
3
+ size 19541595
checkpoint_1007000/target.decoder.layers_10.mlp.wi_1.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83042746d513b560f5717a8a4abd5b4498f7b893cf4422a521b7ebe5a028f3c4
3
+ size 19541287
checkpoint_1007000/target.decoder.layers_14.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.decoder.layers_14.mlp.wi_0.kernel/.zarray.__tmp1284481477073725886.~1663960300551089~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/.zarray.__tmp13030154618658172265.~1663960300421589~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/.zarray.__tmp13061122469800148957.~1663960300873570~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/.zarray.__tmp13391909884930776585.~1663960300421563~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/.zarray.__tmp2880886554391784844.~1663960300780176~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/.zarray.__tmp3361864013994727667.~1663960300602674~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/.zarray.__tmp6305757313857656718.~1663960300683740~ ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,1280],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,10240],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee7cdc0e5118e930fa9fe79b1d3550121aeebada108655ad9ec8975df0695361
3
+ size 19531603
checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440b64e37f0e8deb1df25dd7305bc218290bdf60642e4fdf47b814e5bf14f24a
3
+ size 19531917
checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0671ed43c3c80e5d91d1f7a650e952df4166623702fc353dfd557d0c37cf4a78
3
+ size 19532569
checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:218e4614feafcfee7fca7c29326b21bf0753e21dbe3d57dcb3d9077490dfebc0
3
+ size 19533198
checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a44dda0fef7031a60cbff3de124ed4b8de67510a966ffb4795fed5b03e770b2
3
+ size 19531764
checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1855c2621e40ce9f2637a130fffb9c4aefa9ecd785e322bd3d7bafaaa032b83
3
+ size 19531720
checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35bef46a9e1604b086138ea82b07967e9e7f8e97446a6ec55176276ab0cc18e4
3
+ size 19531316
checkpoint_1007000/target.decoder.layers_14.mlp.wi_0.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f57cd172d7b1eba5ff21329984f3b08e7ded48eb407ae8cce9f8e0ba3aae904
3
+ size 19531816
checkpoint_1007000/target.decoder.layers_15.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_15.pre_self_attention_layer_norm.scale/0 ADDED
Binary file (14.6 kB). View file
 
checkpoint_1007000/target.decoder.layers_17.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_17.pre_cross_attention_layer_norm.scale/0 ADDED
Binary file (14.8 kB). View file
 
checkpoint_1007000/target.decoder.layers_19.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_19.pre_self_attention_layer_norm.scale/0 ADDED
Binary file (14.2 kB). View file
 
checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[512,4096],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
checkpoint_1007000/target.decoder.layers_20.self_attention.out.kernel/.zarray.__tmp10498699521731813312.~1663960300989010~ 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_20.self_attention.out.kernel/.zarray.__tmp17907976336290164547.~1663960300548811~ 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_20.self_attention.out.kernel/.zarray.__tmp2275540253024918713.~1663960300987387~ 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_20.self_attention.out.kernel/.zarray.__tmp3308913374843981282.~1663960300599989~ 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_20.self_attention.out.kernel/.zarray.__tmp8132968568760133378.~1663960300688721~ 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_20.self_attention.out.kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c20c11bc002c74e75687a0b46c84a502c6edff93184df310746e06ff23be90d
3
+ size 7804682