Hugging Face's logo

bigscience
/
mt0-t5x

Model card Files
xet
Community
TimeRobber commited on
Commit
0e11993
·
1 Parent(s): 340102f

Upload part 3

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 +53 -0
  2. checkpoint_1007000/state.param_states.decoder.layers_15.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  3. checkpoint_1007000/state.param_states.decoder.layers_15.pre_mlp_layer_norm.scale.v/0 +0 -0
  4. checkpoint_1007000/state.param_states.decoder.layers_2.pre_self_attention_layer_norm.scale.v/.zarray +1 -0
  5. checkpoint_1007000/state.param_states.decoder.layers_2.pre_self_attention_layer_norm.scale.v/0 +0 -0
  6. checkpoint_1007000/state.param_states.encoder.layers_4.pre_attention_layer_norm.scale.v/.zarray +1 -0
  7. checkpoint_1007000/state.param_states.encoder.layers_4.pre_attention_layer_norm.scale.v/0 +0 -0
  8. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/.zarray +1 -0
  9. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/.zarray.__tmp10961565108918062831.~1663960300886268~ +1 -0
  10. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/.zarray.__tmp11793943505122929052.~1663960300505221~ +1 -0
  11. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/.zarray.__tmp1440098945699490157.~1663960300551568~ +1 -0
  12. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/.zarray.__tmp14628425770511553113.~1663960300312599~ +1 -0
  13. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/.zarray.__tmp18297844883934390469.~1663960300494925~ +1 -0
  14. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/.zarray.__tmp5864613505269189558.~1663960300425303~ +1 -0
  15. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.0 +3 -0
  16. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.1 +3 -0
  17. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.2 +3 -0
  18. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.3 +3 -0
  19. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.4 +3 -0
  20. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.5 +3 -0
  21. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.6 +3 -0
  22. checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.7 +3 -0
  23. checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/0.0 +3 -0
  24. checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/1.0 +3 -0
  25. checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/3.0 +3 -0
  26. checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/6.0 +3 -0
  27. checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/7.0 +3 -0
  28. checkpoint_1007000/target.decoder.layers_22.pre_cross_attention_layer_norm.scale/.zarray +1 -0
  29. checkpoint_1007000/target.decoder.layers_22.pre_cross_attention_layer_norm.scale/0 +0 -0
  30. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/.zarray +1 -0
  31. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/.zarray.__tmp12830070173218396735.~1663960300549727~ +1 -0
  32. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/.zarray.__tmp13183448119106705620.~1663960300385289~ +1 -0
  33. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/.zarray.__tmp15752704559821348252.~1663960300686341~ +1 -0
  34. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/.zarray.__tmp464211840814670155.~1663960300776596~ +1 -0
  35. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/.zarray.__tmp6750169135918407256.~1663960300872835~ +1 -0
  36. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/.zarray.__tmp7187338248637227935.~1663960300886001~ +1 -0
  37. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/.zarray.__tmp9319007599745864122.~1663960300351256~ +1 -0
  38. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/0.0 +3 -0
  39. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/1.0 +3 -0
  40. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/2.0 +3 -0
  41. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/3.0 +3 -0
  42. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/4.0 +3 -0
  43. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/5.0 +3 -0
  44. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/6.0 +3 -0
  45. checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/7.0 +3 -0
  46. checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/.zarray +1 -0
  47. checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/.zarray.__tmp11933270201289857914.~1663960300307662~ +1 -0
  48. checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/.zarray.__tmp1696731562003538842.~1663960300312759~ +1 -0
  49. checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.0 +3 -0
  50. checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.1 +3 -0
.gitattributes CHANGED
@@ -171,3 +171,56 @@ checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.5 filter=lfs diff=
171
  checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
172
  checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
173
  checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
171
  checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
172
  checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
173
  checkpoint_1007000/target.decoder.layers_15.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
174
+ checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
175
+ checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
176
+ checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
177
+ checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
178
+ checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
179
+ checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
180
+ checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
181
+ checkpoint_1007000/target.encoder.layers_17.mlp.wi_0.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
182
+ checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
183
+ checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
184
+ checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
185
+ checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
186
+ checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
187
+ checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
188
+ checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
189
+ checkpoint_1007000/target.decoder.layers_4.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
190
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
191
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
192
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
193
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
194
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
195
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
196
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
197
+ checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
198
+ checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
199
+ checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
200
+ checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
201
+ checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
202
+ checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
203
+ checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/5.0 filter=lfs diff=lfs merge=lfs -text
204
+ checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/2.0 filter=lfs diff=lfs merge=lfs -text
205
+ checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/4.0 filter=lfs diff=lfs merge=lfs -text
206
+ checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
207
+ checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
208
+ checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
209
+ checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
210
+ checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
211
+ checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
212
+ checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
213
+ checkpoint_1007000/target.encoder.layers_18.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
214
+ checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
215
+ checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
216
+ checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
217
+ checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
218
+ checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
219
+ checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
220
+ checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
221
+ checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
222
+ checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/6.0 filter=lfs diff=lfs merge=lfs -text
223
+ checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/1.0 filter=lfs diff=lfs merge=lfs -text
224
+ checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/3.0 filter=lfs diff=lfs merge=lfs -text
225
+ checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
226
+ checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/7.0 filter=lfs diff=lfs merge=lfs -text
checkpoint_1007000/state.param_states.decoder.layers_15.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_15.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (14.9 kB). View file
 
checkpoint_1007000/state.param_states.decoder.layers_2.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_2.pre_self_attention_layer_norm.scale.v/0 ADDED
Binary file (14.9 kB). View file
 
checkpoint_1007000/state.param_states.encoder.layers_4.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_4.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (15.3 kB). View file
 
checkpoint_1007000/target.decoder.layers_11.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_11.encoder_decoder_attention.value.kernel/.zarray.__tmp10961565108918062831.~1663960300886268~ 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.encoder_decoder_attention.value.kernel/.zarray.__tmp11793943505122929052.~1663960300505221~ 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.encoder_decoder_attention.value.kernel/.zarray.__tmp1440098945699490157.~1663960300551568~ 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.encoder_decoder_attention.value.kernel/.zarray.__tmp14628425770511553113.~1663960300312599~ 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.encoder_decoder_attention.value.kernel/.zarray.__tmp18297844883934390469.~1663960300494925~ 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.encoder_decoder_attention.value.kernel/.zarray.__tmp5864613505269189558.~1663960300425303~ 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.encoder_decoder_attention.value.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90c9202ca5e5fb3a2aa8667ebc11c696e348c7d7294a4f486ccdd7617959c0b5
3
+ size 7807159
checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:569e5d696789228c98b20d6eadc4c084b39d92d16de38cd26847217f6f8f9aa4
3
+ size 7803093
checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d19aae8e6a35d38ea596e8172a5c0a4f8f3f7f480dd7b006d498593d48e41d1a
3
+ size 7800620
checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c376752ee217f9e951b7817b95616974b9671068f0661cddc7db8812775ea3fe
3
+ size 7800512
checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2197d856500ad390245050f46333b81f46bcfc1ae18f2bd33567254cb44810f
3
+ size 7802077
checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d712262698bf9d323568301ee3309c5ce4da7b39e6fd23998de227b90012378f
3
+ size 7801706
checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8e206778aebad42372c5be8e83536ff04d60b1f0000f76f30c7dea8472aa883
3
+ size 7801882
checkpoint_1007000/target.decoder.layers_11.encoder_decoder_attention.value.kernel/0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b2eb1e8a794bab31e1efb00844560b8f03b47a3b7dd48a3ac371a2e2897c52a
3
+ size 7801473
checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb22f13224efe375960573e53d76fba304b3060484ee22dd2155a76a3cfd0b6
3
+ size 7820889
checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e56680b2d21f9d8572593eb66ab7570bc2892be102b49c6046415bcc17fc270c
3
+ size 7819170
checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35a63d62b381ece9da62fc3914d1123a58d2dc109aa0e4a93d7fa9be391d207
3
+ size 7820038
checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b7b0ac3a91278650e3b24d806f278487abcb420087fa54230895a5ca8f6c6f6
3
+ size 7820254
checkpoint_1007000/target.decoder.layers_13.encoder_decoder_attention.out.kernel/7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b09510f34d4be78e56384341a5c8806819a24e2f2e37bbb65a0c882eb171602
3
+ size 7819902
checkpoint_1007000/target.decoder.layers_22.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_22.pre_cross_attention_layer_norm.scale/0 ADDED
Binary file (14.4 kB). View file
 
checkpoint_1007000/target.decoder.layers_23.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_23.self_attention.out.kernel/.zarray.__tmp12830070173218396735.~1663960300549727~ 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.self_attention.out.kernel/.zarray.__tmp13183448119106705620.~1663960300385289~ 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.self_attention.out.kernel/.zarray.__tmp15752704559821348252.~1663960300686341~ 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.self_attention.out.kernel/.zarray.__tmp464211840814670155.~1663960300776596~ 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.self_attention.out.kernel/.zarray.__tmp6750169135918407256.~1663960300872835~ 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.self_attention.out.kernel/.zarray.__tmp7187338248637227935.~1663960300886001~ 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.self_attention.out.kernel/.zarray.__tmp9319007599745864122.~1663960300351256~ 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.self_attention.out.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd961bf37fbec24764a16aff20a002216bf3f7c82f5c860c9f0328814e3a911
3
+ size 7799538
checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:994beed721b0806bd963f744990ae598e74b053cd8d7f4e75401b2d155d93d00
3
+ size 7805374
checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:403f162887853ea97a5ea44c2125300183656ae2e01874a801effa941b002509
3
+ size 7803732
checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55952d638b3750fb9d99b95da16da4c2a9687799018c95a6259d6ec895235565
3
+ size 7810296
checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a564ef1e01718bd811b4880b32a4015f4469db6f02ea8e2964ceb6c9813fe8
3
+ size 7807573
checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ded9f6261b5cc982f4e06136bc32bebc20f767d262b4b4333d855cbb90dee23d
3
+ size 7803713
checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f0d9e5cc20927dea18009eaab2e46825e460ee6e48391e57738bd074943b2a
3
+ size 7801571
checkpoint_1007000/target.decoder.layers_23.self_attention.out.kernel/7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2416339f505940a7e7dbbd87b4a6dcfb7648dfa2650ec1aaed129cb72331336
3
+ size 7805580
checkpoint_1007000/target.decoder.layers_3.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_3.encoder_decoder_attention.value.kernel/.zarray.__tmp11933270201289857914.~1663960300307662~ 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_3.encoder_decoder_attention.value.kernel/.zarray.__tmp1696731562003538842.~1663960300312759~ 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_3.encoder_decoder_attention.value.kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfe31aad0748136710555d63a57daed3dcd52bfa3a7fcad3fc3ac7cbeb05231b
3
+ size 7817313
checkpoint_1007000/target.decoder.layers_3.encoder_decoder_attention.value.kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0db9fe80e418090a1aa80abfb1769af91fb6eafe0b822c2cb343afaec0e503dc
3
+ size 7825741