Hugging Face's logo

bigscience
/
mt0-t5x

Model card Files Community
TimeRobber commited on
Commit
651860e
·
1 Parent(s): 9771a53

Upload part 43

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 +51 -0
  2. checkpoint_1007000/state.param_states.decoder.layers_18.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
  3. checkpoint_1007000/state.param_states.decoder.layers_18.pre_cross_attention_layer_norm.scale.v/0 +0 -0
  4. checkpoint_1007000/state.param_states.encoder.layers_2.pre_attention_layer_norm.scale.v/.zarray +1 -0
  5. checkpoint_1007000/state.param_states.encoder.layers_2.pre_attention_layer_norm.scale.v/0 +0 -0
  6. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/.zarray +1 -0
  7. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/.zarray.__tmp10901794004346949036.~1663960299724948~ +1 -0
  8. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/.zarray.__tmp11257918630370621898.~1663960300016140~ +1 -0
  9. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/.zarray.__tmp16908940089072778477.~1663960300134064~ +1 -0
  10. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/.zarray.__tmp7027389052965847199.~1663960299834567~ +1 -0
  11. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/0.0 +3 -0
  12. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/1.0 +3 -0
  13. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/2.0 +3 -0
  14. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/3.0 +3 -0
  15. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/4.0 +3 -0
  16. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/5.0 +3 -0
  17. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/6.0 +3 -0
  18. checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/7.0 +3 -0
  19. checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/.zarray +1 -0
  20. checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/.zarray.__tmp2259872716008492990.~1663960300307720~ +1 -0
  21. checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/.zarray.__tmp4017084296749785024.~1663960300493069~ +1 -0
  22. checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/.zarray.__tmp4645164090967239225.~1663960300550732~ +1 -0
  23. checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.0 +3 -0
  24. checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.1 +3 -0
  25. checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.2 +3 -0
  26. checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.3 +3 -0
  27. checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.4 +3 -0
  28. checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.5 +3 -0
  29. checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.6 +3 -0
  30. checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.7 +3 -0
  31. checkpoint_1007000/target.decoder.layers_13.pre_mlp_layer_norm.scale/.zarray +1 -0
  32. checkpoint_1007000/target.decoder.layers_13.pre_mlp_layer_norm.scale/0 +0 -0
  33. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/.zarray.__tmp7773181149882067999.~1663960300465598~ +1 -0
  34. checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.4 +3 -0
  35. checkpoint_1007000/target.decoder.layers_16.pre_cross_attention_layer_norm.scale/.zarray +1 -0
  36. checkpoint_1007000/target.decoder.layers_16.pre_cross_attention_layer_norm.scale/0 +0 -0
  37. checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/.zarray +1 -0
  38. checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/.zarray.__tmp10496619256372905667.~1663960301113131~ +1 -0
  39. checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/.zarray.__tmp10678456478467708649.~1663960300600380~ +1 -0
  40. checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/.zarray.__tmp10681564760674261110.~1663960300685570~ +1 -0
  41. checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/.zarray.__tmp13740049416071444263.~1663960300548400~ +1 -0
  42. checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/.zarray.__tmp17467392749215918859.~1663960300554127~ +1 -0
  43. checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/.zarray.__tmp4439840698657571479.~1663960300729466~ +1 -0
  44. checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/.zarray.__tmp5747035392819332771.~1663960300461976~ +1 -0
  45. checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/0.0 +3 -0
  46. checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/1.0 +3 -0
  47. checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/2.0 +3 -0
  48. checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/3.0 +3 -0
  49. checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/4.0 +3 -0
  50. checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/5.0 +3 -0
.gitattributes CHANGED
@@ -2186,3 +2186,54 @@ checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel
2186
  checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2187
  checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2188
  checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2186
  checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2187
  checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2188
  checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2189
+ checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2190
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
2191
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
2192
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
2193
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2194
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
2195
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
2196
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
2197
+ checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
2198
+ checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2199
+ checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2200
+ checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2201
+ checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2202
+ checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2203
+ checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2204
+ checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2205
+ checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2206
+ checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
2207
+ checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
2208
+ checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
2209
+ checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2210
+ checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
2211
+ checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
2212
+ checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
2213
+ checkpoint_1007000/target.encoder.layers_19.mlp.wo.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
2214
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2215
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2216
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2217
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2218
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2219
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2220
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
2221
+ checkpoint_1007000/target.decoder.layers_5.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
2222
+ checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
2223
+ checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
2224
+ checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
2225
+ checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2226
+ checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
2227
+ checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
2228
+ checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
2229
+ checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
2230
+ checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
2231
+ checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
2232
+ checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
2233
+ checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
2234
+ checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
2235
+ checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
2236
+ checkpoint_1007000/target.encoder.layers_4.attention.value.kernel/0.2 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
checkpoint_1007000/state.param_states.decoder.layers_18.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_18.pre_cross_attention_layer_norm.scale.v/0 ADDED
Binary file (14.7 kB). View file
 
checkpoint_1007000/state.param_states.encoder.layers_2.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_2.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (15.2 kB). View file
 
checkpoint_1007000/target.decoder.layers_10.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_10.encoder_decoder_attention.out.kernel/.zarray.__tmp10901794004346949036.~1663960299724948~ 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_10.encoder_decoder_attention.out.kernel/.zarray.__tmp11257918630370621898.~1663960300016140~ 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_10.encoder_decoder_attention.out.kernel/.zarray.__tmp16908940089072778477.~1663960300134064~ 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_10.encoder_decoder_attention.out.kernel/.zarray.__tmp7027389052965847199.~1663960299834567~ 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_10.encoder_decoder_attention.out.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0bfa0ba4dfe7927210d1e45d6e8db2c6355870109d26b75d4dacd7f0cf876f1
3
+ size 7818701
checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08aa08e42608ae9a4c4a7f06309cf00f5898412af8a00d9e921e55b86f43b96b
3
+ size 7819200
checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6772454cc9c1d89604feb2047f14402da85d6de59101a0c614e896485a736393
3
+ size 7820011
checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a40636b2abef7c533963cf3d496668c07beef9c55a293a8ef4c9c1eebbcd3d41
3
+ size 7818996
checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90b3fae1f64016faf7f3f394eae0000274f8e91231c92d6e23e1cf5f880a79cc
3
+ size 7820072
checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac188f8e608e21e574bd7cf20ea82b7721bfe98954b85055c2ecae3212f6f860
3
+ size 7819032
checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b549b16e6b0c0abef86b72320396e1e9d1ec551e177970ad682b77d905c63e1
3
+ size 7818971
checkpoint_1007000/target.decoder.layers_10.encoder_decoder_attention.out.kernel/7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695895998c58671546f52ceba6699dc5b2f9d1951efc010a7ed05863ce1e3abd
3
+ size 7819268
checkpoint_1007000/target.decoder.layers_11.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_11.self_attention.query.kernel/.zarray.__tmp2259872716008492990.~1663960300307720~ 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_11.self_attention.query.kernel/.zarray.__tmp4017084296749785024.~1663960300493069~ 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_11.self_attention.query.kernel/.zarray.__tmp4645164090967239225.~1663960300550732~ 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_11.self_attention.query.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdeb84fdf5093d33a1b20d57979cdc10e9b21f4ac42a961c2bcee6771b6d6558
3
+ size 7823184
checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6f9ba034f203643b0929d3120a3edc42dfabe4e41156728a75cdcab589db951
3
+ size 7821505
checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b3ba7d810e55c0ac02684c894621f08757d08f92f20d2ba3cc77d0f337124f8
3
+ size 7824566
checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e777a6a2aef87fc2ab3eead195bb2a6d8ae6e603783ee6d930d70135c5a732a
3
+ size 7809681
checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74eed10d369be05bfbb16bb57f98f0f8b9bfd91dfd9ca921c218a8d6521b6664
3
+ size 7834345
checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cf4f77422b7c37f2c41dd7e50a284b238ab09e542a483bf111c97c3f73c5c8e
3
+ size 7809623
checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252b3530516ce5f7f05d5e9aa2a3b90e6da77394b085996dd2dbddf735646ed3
3
+ size 7808901
checkpoint_1007000/target.decoder.layers_11.self_attention.query.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2264e63c7e089080a3ad9515cc9dd0a6ae92b445295a90cb9eef150ea1e07da7
3
+ size 7810608
checkpoint_1007000/target.decoder.layers_13.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_13.pre_mlp_layer_norm.scale/0 ADDED
Binary file (14.6 kB). View file
 
checkpoint_1007000/target.decoder.layers_14.encoder_decoder_attention.key.kernel/.zarray.__tmp7773181149882067999.~1663960300465598~ 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.encoder_decoder_attention.key.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fcab08d7dcc2ad22f97ceed0d799f6f601933cf467d206b8fa648b8f9ccfcbe
3
+ size 7817225
checkpoint_1007000/target.decoder.layers_16.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_16.pre_cross_attention_layer_norm.scale/0 ADDED
Binary file (14.8 kB). View file
 
checkpoint_1007000/target.decoder.layers_16.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_16.self_attention.out.kernel/.zarray.__tmp10496619256372905667.~1663960301113131~ 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_16.self_attention.out.kernel/.zarray.__tmp10678456478467708649.~1663960300600380~ 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_16.self_attention.out.kernel/.zarray.__tmp10681564760674261110.~1663960300685570~ 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_16.self_attention.out.kernel/.zarray.__tmp13740049416071444263.~1663960300548400~ 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_16.self_attention.out.kernel/.zarray.__tmp17467392749215918859.~1663960300554127~ 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_16.self_attention.out.kernel/.zarray.__tmp4439840698657571479.~1663960300729466~ 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_16.self_attention.out.kernel/.zarray.__tmp5747035392819332771.~1663960300461976~ 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_16.self_attention.out.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9929f092ea0f4c4d9a2389581b718cb62a938cb3f659fb062b9aa10f52cb3446
3
+ size 7810100
checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad142c25f39d9388cc96c9afcaf87444a3da5855ea0046496841956563c63cd
3
+ size 7812047
checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c15c651862623e93ca73d5e7d2eb4559f37a22bd43b12a1c6199da8d6d91d3
3
+ size 7810542
checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88bf91c6da88b47a443e83a940ff3bd6ebf8425c9996d20a52e637f2a1e950d2
3
+ size 7808553
checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:580a0b9f0d1030b16fce28289790c1edf7dd76b68358c508ea5cd2f7506bb9f7
3
+ size 7813724
checkpoint_1007000/target.decoder.layers_16.self_attention.out.kernel/5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c6de1a08ecbc5e67d98cf55d723998427c1eb460dee9d5f9a0b09857fc50692
3
+ size 7812555