Add 100k train step and HF flax model
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint_100000/checkpoint +3 -0
- checkpoint_100000/state.param_states.decoder.decoder_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.decoder_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_10.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_10.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_10.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_10.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_10.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_10.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_11.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_11.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_11.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_11.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_11.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_11.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_12.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_12.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_12.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_12.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_12.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_12.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_13.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_13.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_13.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_13.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_14.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_14.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_14.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_14.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_14.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_14.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_15.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_15.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_15.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_100000/state.param_states.decoder.layers_15.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_100000/state.param_states.decoder.layers_15.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
checkpoint_100000/checkpoint
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:148433a78c7b8e9f72386ce63e1e3b7f55c98a3c2cc8b992cc064f1ca6f7d7e4
|
3 |
+
size 3106377
|
checkpoint_100000/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_100000/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 sha256:6c1886560db589d78c79d1d6dba5c5dc69e2dbacf6389309ccd3aa365a8ebbeb
|
3 |
+
size 1865
|
checkpoint_100000/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_100000/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:d734c3eb2ab0f948caaf41fbbce2359d768afdd08e714b910525768b8e82487b
|
3 |
+
size 1961
|
checkpoint_100000/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_100000/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:f4777b1092f0bcaacb89fb2186fac57ccd36cbcc26d1655c5d26320df17fd8b9
|
3 |
+
size 1954
|
checkpoint_100000/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_100000/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 sha256:20ea3b5b47276e838badc7add2d836742d1ed5d603fbb3c55dbefd79ae2bfe92
|
3 |
+
size 1954
|
checkpoint_100000/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_100000/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 sha256:3b4d4a34beba368f81d273072a272c15e262f91e1d2cbbddc4490d5227d24136
|
3 |
+
size 1953
|
checkpoint_100000/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_100000/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 sha256:84c3f57a3c1ab6465ad6f2a560171b3157acd4f92672c069cb9c33e8a2097c67
|
3 |
+
size 1959
|
checkpoint_100000/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_100000/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 sha256:4c8b074b2a5e2c3847c3e3656854f13397acbf16d350865b9b792d0b8bae1a86
|
3 |
+
size 1946
|
checkpoint_100000/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_100000/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:e8599f6d6cbf436ebd1eeb242068bf5031a89a82a0b8c6906d07b8411820cf07
|
3 |
+
size 1869
|
checkpoint_100000/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_100000/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 sha256:7c0660789ec5291be56e18bac430cbb1481c233fb32c20a8c3e3032d5b31a633
|
3 |
+
size 1860
|
checkpoint_100000/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_100000/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 sha256:9300e8d7fc40b36a4525e006b0ecfa2607f3ac81a5bc77d7479ddbbf962688d7
|
3 |
+
size 1886
|
checkpoint_100000/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_100000/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 sha256:4041cf2cd5c94b8e6f09ba91c37d0aedac02a8b19d36a2ae78435887ef3c8ba5
|
3 |
+
size 1880
|
checkpoint_100000/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_100000/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 sha256:398b1968f77114ff28975ef9ef39aa7b825dfbcefa7798374922c9db14676a6a
|
3 |
+
size 1873
|
checkpoint_100000/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_100000/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 sha256:1364de356317711394a26e10d607b30cd4b3414b5e98315538f65e34258a9df1
|
3 |
+
size 1876
|
checkpoint_100000/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_100000/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:aa667ecd2c88e9b557ddf23153e3f16b0307f41852aa01dccdac03ce0a70bcc6
|
3 |
+
size 1841
|
checkpoint_100000/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_100000/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 sha256:84f3e9baa868b0f17dfcf8041c86aed574b7cdbfc22f377c498c4b9c8265e36e
|
3 |
+
size 1873
|
checkpoint_100000/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_100000/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:ef2da3481de105a2c7dc79f18269a11ea6425166619bd138fd4573fabbac5dd3
|
3 |
+
size 1881
|
checkpoint_100000/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_100000/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:d2aad294da92cecc25ac5f509f0bb8e978febd9a9f6a0b8f369996e24d5cfaba
|
3 |
+
size 1842
|
checkpoint_100000/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_100000/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:f788567a1f67a6e2d8e524e3687a46c370bc6b29f1c3d5eaa32175e2f11ca4be
|
3 |
+
size 1858
|
checkpoint_100000/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_100000/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 sha256:4403c745af860fc867043d1f606bc11f938dbc607f391deba1d98f2de83cdcc7
|
3 |
+
size 1883
|
checkpoint_100000/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_100000/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 sha256:1ec1b3e291ac1ba2cfe7735363b9ea79848fb08b3c7aa6f8b6c7a231ee8baff4
|
3 |
+
size 1879
|
checkpoint_100000/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_100000/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:e20c38272028dfcea38e1c1611ac23616e367c1479c3505a18a11b8fa0c2487d
|
3 |
+
size 1833
|
checkpoint_100000/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_100000/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:f6f765d60c4caffb1b5942da6d04c1bcb49f757d3b979936e67800faa2c6db9b
|
3 |
+
size 1835
|
checkpoint_100000/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_100000/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:a5f5b9e59cbcda611df0aa3efc0aac0d67b3118b6f6cfe8118e8faf526d86426
|
3 |
+
size 1858
|
checkpoint_100000/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_100000/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:f37fb907959ad3516f7b5b8d5c6520b265548b6a6ecc2b245457d9a5b9f030cc
|
3 |
+
size 1870
|
checkpoint_100000/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
|