Commit
·
7ff1e80
1
Parent(s):
9285b52
Upload part 7
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +50 -0
- checkpoint_1007000/state.param_states.decoder.layers_16.pre_cross_attention_layer_norm.scale.v/.zarray +1 -0
- checkpoint_1007000/state.param_states.decoder.layers_16.pre_cross_attention_layer_norm.scale.v/0 +0 -0
- checkpoint_1007000/state.param_states.decoder.relpos_bias.rel_embedding.v/6.0 +0 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/.zarray.__tmp13328261150242145534.~1663960300776998~ +1 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/.zarray.__tmp14859958618190164091.~1663960300467381~ +1 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/.zarray.__tmp15442127706563651536.~1663960300622060~ +1 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/.zarray.__tmp2169926733390421364.~1663960300863590~ +1 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/.zarray.__tmp5096204140951894811.~1663960300724827~ +1 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/.zarray.__tmp6599579301873965711.~1663960300889059~ +1 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/.zarray.__tmp9146290015084521214.~1663960300779126~ +1 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.3 +3 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/.zarray.__tmp11905897875462043321.~1663960300941097~ +1 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/.zarray.__tmp12032141427906967315.~1663960300471395~ +1 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/.zarray.__tmp12366640530846218561.~1663960300497792~ +1 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/.zarray.__tmp13432700872246250849.~1663960300495596~ +1 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/.zarray.__tmp15700723738782736220.~1663960300626178~ +1 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/.zarray.__tmp4248205230881319111.~1663960300724201~ +1 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/.zarray.__tmp7527782868157639178.~1663960300420415~ +1 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.0 +3 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.1 +3 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.3 +3 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.5 +3 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.6 +3 -0
- checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.7 +3 -0
- checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/.zarray.__tmp12720901510908714668.~1663960300468386~ +1 -0
- checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/.zarray.__tmp13836621873047710726.~1663960300937456~ +1 -0
- checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.2 +3 -0
- checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.4 +3 -0
- checkpoint_1007000/target.decoder.layers_9.pre_mlp_layer_norm.scale/.zarray +1 -0
- checkpoint_1007000/target.decoder.layers_9.pre_mlp_layer_norm.scale/0 +0 -0
- checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/.zarray +1 -0
- checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/.zarray.__tmp12272279728897468310.~1663960300599910~ +1 -0
- checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/.zarray.__tmp12284065011570034403.~1663960300776944~ +1 -0
- checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/.zarray.__tmp14249805561749006881.~1663960300725987~ +1 -0
- checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/.zarray.__tmp16744412138986692617.~1663960300607765~ +1 -0
- checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/.zarray.__tmp4821097839245769492.~1663960300937420~ +1 -0
- checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/.zarray.__tmp670871110100812199.~1663960300686232~ +1 -0
- checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/.zarray.__tmp6835726713105326890.~1663960300872903~ +1 -0
.gitattributes
CHANGED
|
@@ -369,3 +369,53 @@ checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.0 filter=lfs diff=l
|
|
| 369 |
checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 370 |
checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 371 |
checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 369 |
checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 370 |
checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 371 |
checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 372 |
+
checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 373 |
+
checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 374 |
+
checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 375 |
+
checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 376 |
+
checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 377 |
+
checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 378 |
+
checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 379 |
+
checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 380 |
+
checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 381 |
+
checkpoint_1007000/target.encoder.layers_11.attention.value.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 382 |
+
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 383 |
+
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 384 |
+
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 385 |
+
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 386 |
+
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 387 |
+
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 388 |
+
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 389 |
+
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 390 |
+
checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 391 |
+
checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 392 |
+
checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 393 |
+
checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 394 |
+
checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 395 |
+
checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 396 |
+
checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 397 |
+
checkpoint_1007000/target.encoder.layers_10.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 398 |
+
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 399 |
+
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 400 |
+
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 401 |
+
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 402 |
+
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 403 |
+
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 404 |
+
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 405 |
+
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 406 |
+
checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 407 |
+
checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 408 |
+
checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 409 |
+
checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 410 |
+
checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 411 |
+
checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 412 |
+
checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 413 |
+
checkpoint_1007000/target.encoder.layers_5.attention.key.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
| 414 |
+
checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 415 |
+
checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.7 filter=lfs diff=lfs merge=lfs -text
|
| 416 |
+
checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 417 |
+
checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.6 filter=lfs diff=lfs merge=lfs -text
|
| 418 |
+
checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.5 filter=lfs diff=lfs merge=lfs -text
|
| 419 |
+
checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 420 |
+
checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 421 |
+
checkpoint_1007000/target.encoder.layers_12.attention.query.kernel/0.4 filter=lfs diff=lfs merge=lfs -text
|
checkpoint_1007000/state.param_states.decoder.layers_16.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_16.pre_cross_attention_layer_norm.scale.v/0
ADDED
|
Binary file (15 kB). View file
|
|
|
checkpoint_1007000/state.param_states.decoder.relpos_bias.rel_embedding.v/6.0
ADDED
|
Binary file (1.02 kB). View file
|
|
|
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_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_17.encoder_decoder_attention.query.kernel/.zarray.__tmp13328261150242145534.~1663960300776998~
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_17.encoder_decoder_attention.query.kernel/.zarray.__tmp14859958618190164091.~1663960300467381~
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_17.encoder_decoder_attention.query.kernel/.zarray.__tmp15442127706563651536.~1663960300622060~
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_17.encoder_decoder_attention.query.kernel/.zarray.__tmp2169926733390421364.~1663960300863590~
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_17.encoder_decoder_attention.query.kernel/.zarray.__tmp5096204140951894811.~1663960300724827~
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_17.encoder_decoder_attention.query.kernel/.zarray.__tmp6599579301873965711.~1663960300889059~
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_17.encoder_decoder_attention.query.kernel/.zarray.__tmp9146290015084521214.~1663960300779126~
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_17.encoder_decoder_attention.query.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a35a7310ac179a3c9cbea3947a61a8b6c16407fb089afcbcf771f247e5e5a457
|
| 3 |
+
size 7816401
|
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf13007119e5e94c2a79885caa0d5cbec2d12cfc0ec44fc43bf30bb99f71f122
|
| 3 |
+
size 7817272
|
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4594baae919f358f6912236fb0aeab3273b1e4542fedb326c4523be53a952d4e
|
| 3 |
+
size 7816153
|
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ed21371bc15e18e4abe9a13130653872a1f2aa68af00d626ff2887aa3cb116a
|
| 3 |
+
size 7816217
|
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b58420ec0d83b73decaa15b9a6cf4c1f4b28cd555fea1faeee985b66e1af453
|
| 3 |
+
size 7816620
|
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7197d4b2e94ed8ff5bc0127cfdf513bc88d81a6663fd1e53f23dbefc18dc831e
|
| 3 |
+
size 7816562
|
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2519722f200d5995af38fd4795889ed79e648e967be4beb4bc8789d83cead384
|
| 3 |
+
size 7816971
|
checkpoint_1007000/target.decoder.layers_17.encoder_decoder_attention.query.kernel/0.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a11a938464b4da6a3f865f035dbae8c292829b6268ee7f9c25d57f5b0bafeaf8
|
| 3 |
+
size 7816690
|
checkpoint_1007000/target.decoder.layers_20.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_20.encoder_decoder_attention.key.kernel/.zarray.__tmp11905897875462043321.~1663960300941097~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/.zarray.__tmp12032141427906967315.~1663960300471395~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/.zarray.__tmp12366640530846218561.~1663960300497792~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/.zarray.__tmp13432700872246250849.~1663960300495596~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/.zarray.__tmp15700723738782736220.~1663960300626178~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/.zarray.__tmp4248205230881319111.~1663960300724201~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/.zarray.__tmp7527782868157639178.~1663960300420415~
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chunks":[4096,512],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
|
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:291ab07aced179bb176f305617d14597d4f4e9ef0a5fb8a2a301ed6d07044b96
|
| 3 |
+
size 7801986
|
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb2c8496030b3d9be0d2f12d765b2b65e08bf3a3ce598ea3add975b647528b60
|
| 3 |
+
size 7805008
|
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:476be15b3579693b97e15d4422839dea9a4df3f4738d01a5e4bdb7b42848e32f
|
| 3 |
+
size 7805148
|
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2057bd82847a20b60066e1c2ba9dcd39664e3c32b0b57c4ed8223c5e2f95bbdb
|
| 3 |
+
size 7802875
|
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37f9784e4b55892bee1b0b630adb62192f92cd8645324589cea9b6cd85f2b3e5
|
| 3 |
+
size 7803380
|
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c7ec34bcb90c210d5988bdf5060971d2d59a35914586df67374b78ca2605942
|
| 3 |
+
size 7802933
|
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50626c828b8509a8b85d99c15dbacc8897ec3dc1d2bf568bb9d1cfe8e9d55024
|
| 3 |
+
size 7802867
|
checkpoint_1007000/target.decoder.layers_20.encoder_decoder_attention.key.kernel/0.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45b96c792776c7828084482e10002b557143057e99421269263d0a5b2e6bd356
|
| 3 |
+
size 7801295
|
checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/.zarray.__tmp12720901510908714668.~1663960300468386~
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_9.mlp.wi_1.kernel/.zarray.__tmp13836621873047710726.~1663960300937456~
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_9.mlp.wi_1.kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f856b6bd814fe57fa6240fd07bbde3636e43bb7188861311766b24abcea34d1b
|
| 3 |
+
size 19541714
|
checkpoint_1007000/target.decoder.layers_9.mlp.wi_1.kernel/0.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:746fbfc5ddb3408806c828593200164ca4314963481552a08d3054c4e132742f
|
| 3 |
+
size 19541980
|
checkpoint_1007000/target.decoder.layers_9.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_9.pre_mlp_layer_norm.scale/0
ADDED
|
Binary file (14.8 kB). View file
|
|
|
checkpoint_1007000/target.encoder.layers_10.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.encoder.layers_10.attention.query.kernel/.zarray.__tmp12272279728897468310.~1663960300599910~
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_10.attention.query.kernel/.zarray.__tmp12284065011570034403.~1663960300776944~
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_10.attention.query.kernel/.zarray.__tmp14249805561749006881.~1663960300725987~
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_10.attention.query.kernel/.zarray.__tmp16744412138986692617.~1663960300607765~
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_10.attention.query.kernel/.zarray.__tmp4821097839245769492.~1663960300937420~
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_10.attention.query.kernel/.zarray.__tmp670871110100812199.~1663960300686232~
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_10.attention.query.kernel/.zarray.__tmp6835726713105326890.~1663960300872903~
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}
|