Add 480k train step and HF flax model
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint_480000/checkpoint +3 -0
- checkpoint_480000/state.param_states.decoder.decoder_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.decoder_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_10.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_10.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_10.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_10.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_10.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_10.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_11.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_11.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_11.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_11.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_11.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_11.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_12.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_12.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_12.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_12.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_12.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_12.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_13.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_13.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_13.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_13.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_14.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_14.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_14.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_14.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_14.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_14.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_15.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_15.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_15.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_480000/state.param_states.decoder.layers_15.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_480000/state.param_states.decoder.layers_15.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
checkpoint_480000/checkpoint
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6878c03602077ac8ca791bdf2115684b858ca96d25475064916005f5ea64e3a8
|
3 |
+
size 3106377
|
checkpoint_480000/state.param_states.decoder.decoder_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.decoder_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c99c239eeb6275a488075102410b662871b62302c445fbe9f6a59d6b71d4e2eb
|
3 |
+
size 1865
|
checkpoint_480000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7de80e836ee0e17dab4f1ae0da1ea145a84c34b86ef5b4d735b00125e38f6d84
|
3 |
+
size 1985
|
checkpoint_480000/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:873fbbe37669eee892dc0c5b448e5b05e9bb9b9cd2ca24014ff4d0d0178e3bca
|
3 |
+
size 1969
|
checkpoint_480000/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a446211019a731ac06046554b0ea671c87b2c37eafe7447745ac4e2f148f372
|
3 |
+
size 1970
|
checkpoint_480000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0f39bc852e0c722aa5d29e4e4cb537bd10bf7719816bea3e9c5693596c47137
|
3 |
+
size 1977
|
checkpoint_480000/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56ed20c8a32f79a16856c1e2d60052b3fcb57cd8d0a581a8a5cbf628cb2d9b5a
|
3 |
+
size 1974
|
checkpoint_480000/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6a2626ff67f4ea3f86ecf12ada4b466db06de8b105800e6d7f3001242288881
|
3 |
+
size 1968
|
checkpoint_480000/state.param_states.decoder.layers_10.pre_cross_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_10.pre_cross_attention_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5bbe720bb4bb77e0e15e6a9c09949d5a6f07f6ce6f948e6e7769dfc1d11fe8c
|
3 |
+
size 1873
|
checkpoint_480000/state.param_states.decoder.layers_10.pre_mlp_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_10.pre_mlp_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d00d39e94f6f063346668271070febf688cb619945899122e8cbb65bb17e3e17
|
3 |
+
size 1833
|
checkpoint_480000/state.param_states.decoder.layers_10.pre_self_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_10.pre_self_attention_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5b54cc69d7a8c44c0e4bb5ce03aa2c38a1e9083722c9c8ae054ba81abfdecfe
|
3 |
+
size 1836
|
checkpoint_480000/state.param_states.decoder.layers_11.pre_cross_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_11.pre_cross_attention_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a839b484068b650a05a316d7ba3b7019070daafa83e266088465e4094863c035
|
3 |
+
size 1834
|
checkpoint_480000/state.param_states.decoder.layers_11.pre_mlp_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_11.pre_mlp_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20c0ecc6f65729a73835b9b94d3c7711e69782caf3fe5934e235a617feb5a505
|
3 |
+
size 1820
|
checkpoint_480000/state.param_states.decoder.layers_11.pre_self_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_11.pre_self_attention_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:567488bad7129d5a6a2c54621caf31c7ab8dd6cc2afc0420df2eedbc797e81d5
|
3 |
+
size 1848
|
checkpoint_480000/state.param_states.decoder.layers_12.pre_cross_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_12.pre_cross_attention_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9cfabcce26a64035844c277be8ee9045cfd54eb983c94de104a3c8e6d331e56
|
3 |
+
size 1886
|
checkpoint_480000/state.param_states.decoder.layers_12.pre_mlp_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_12.pre_mlp_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63a7f3c87a2461a9bc6c87f0afc99c14ebfac43f37c224180e36c6e17026130f
|
3 |
+
size 1825
|
checkpoint_480000/state.param_states.decoder.layers_12.pre_self_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_12.pre_self_attention_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd55f7022801e41a086f305bf8e25e47ac6c939ad535dc9ccad1a3bcdb79d585
|
3 |
+
size 1833
|
checkpoint_480000/state.param_states.decoder.layers_13.pre_cross_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_13.pre_cross_attention_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d37cd2642a1cc0982672897365b23be60fd3adb4594681c0fd15eb53a4d9babe
|
3 |
+
size 1880
|
checkpoint_480000/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae444dd1f5170719bcf399e19291c0f34d266e305e82152ddb8c6b707ad4ae5f
|
3 |
+
size 1828
|
checkpoint_480000/state.param_states.decoder.layers_13.pre_self_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_13.pre_self_attention_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93ec98e2c48d763505c14a2cdf6b4556588b90b333962506b98c90985b03b749
|
3 |
+
size 1830
|
checkpoint_480000/state.param_states.decoder.layers_14.pre_cross_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_14.pre_cross_attention_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a3084f22083a1b1b041aac89b787c9567e8cb1b1ecc49beedcb22b3d6b547e8
|
3 |
+
size 1828
|
checkpoint_480000/state.param_states.decoder.layers_14.pre_mlp_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_14.pre_mlp_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:235f49929004b709fef2acf5f1f643a5113fc5e3403de0c639fe5f4039f8b542
|
3 |
+
size 1822
|
checkpoint_480000/state.param_states.decoder.layers_14.pre_self_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_14.pre_self_attention_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28929a71f2477c908e6c95fbfdeab55b469d3f1ee0c9a95b3fe645622eeb0dda
|
3 |
+
size 1826
|
checkpoint_480000/state.param_states.decoder.layers_15.pre_cross_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_15.pre_cross_attention_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f810d34f1cb54cc3ffb75565e1837c632916382cd65f9bd8f2e4d851df924944
|
3 |
+
size 1848
|
checkpoint_480000/state.param_states.decoder.layers_15.pre_mlp_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|
checkpoint_480000/state.param_states.decoder.layers_15.pre_mlp_layer_norm.scale.v/0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee74d9325fb3b99cab71538ad0e26e54f3a0cad62229fd3b080c654d825f685e
|
3 |
+
size 1823
|
checkpoint_480000/state.param_states.decoder.layers_15.pre_self_attention_layer_norm.scale.v/.zarray
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2047bb2946e4ed6647bcffb79d9f7e17e925d870dad7f5c869dc7ad8429813e
|
3 |
+
size 168
|