Add 200k train step and HF flax model
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint_200000/checkpoint +3 -0
- checkpoint_200000/state.param_states.decoder.decoder_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.decoder_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_10.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_10.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_10.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_10.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_10.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_10.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_11.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_11.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_11.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_11.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_11.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_11.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_12.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_12.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_12.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_12.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_12.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_12.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_13.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_13.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_13.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_13.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_14.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_14.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_14.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_14.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_14.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_14.pre_self_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_15.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_15.pre_cross_attention_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_15.pre_mlp_layer_norm.scale.v/.zarray +3 -0
- checkpoint_200000/state.param_states.decoder.layers_15.pre_mlp_layer_norm.scale.v/0 +3 -0
- checkpoint_200000/state.param_states.decoder.layers_15.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
checkpoint_200000/checkpoint
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a243c389f389934523c1845d2fbebc627e8b507b90e1ed808f1d54827e3fc0d9
|
3 |
+
size 3106377
|
checkpoint_200000/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_200000/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 sha256:3179e83a26a7166e5ca93254d078d1837613db00f2261c35748ef432c0b20634
|
3 |
+
size 1870
|
checkpoint_200000/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_200000/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 sha256:57ba9ad7a23c5f7d599df2894ab11ece4ffd642bf9f68e48ed7ef3b08adb6226
|
3 |
+
size 1916
|
checkpoint_200000/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_200000/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:e223fb70aa7d1f37745dcc6373422bb4b9d9688bc3a247040f2e682f94314293
|
3 |
+
size 1905
|
checkpoint_200000/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_200000/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:aab21b16b841bc3331f90b2d0b077ecfb27e39fe23e90af0fc91969c0ae2624f
|
3 |
+
size 1921
|
checkpoint_200000/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_200000/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:cba8dc7c9fbbc3d2c5baa298605d54b274606c4c25b162c0c4dd0252f6888781
|
3 |
+
size 1935
|
checkpoint_200000/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_200000/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 sha256:0b4b366632cac29987117d842930f89ff04ad3f15b68975f866a562a995de5a3
|
3 |
+
size 1926
|
checkpoint_200000/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_200000/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 sha256:92acfc2b78b8a1f15748e1f3a42d6ada55b3a4182502587d4b64130e82ecf5cd
|
3 |
+
size 1935
|
checkpoint_200000/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_200000/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 sha256:9e90e5c02ce748b248c3de05b3244c202c6bbfdda7c92921c0a67655bdb48e95
|
3 |
+
size 1879
|
checkpoint_200000/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_200000/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:e7b11ee61e14ade0e413cc1544089201a89a90231d935d5d512ed6dfb13f8aaa
|
3 |
+
size 1843
|
checkpoint_200000/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_200000/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:ccccd0b0ab4ea471c480a04974269a3552066f3728e58848c459343d13b95567
|
3 |
+
size 1867
|
checkpoint_200000/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_200000/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:c8dd1fa4a98c75026d4fc18b0b2525db34524cce2f121c3be879acf71f3d2daa
|
3 |
+
size 1837
|
checkpoint_200000/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_200000/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:f632bf09ba59988085c942d7da7ff12b3e4e736b5756209d936384b053471e42
|
3 |
+
size 1823
|
checkpoint_200000/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_200000/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:e97d5089206ead260217e62f20a3fe8503fd6cb3396bdb29f3130a350d3e8583
|
3 |
+
size 1891
|
checkpoint_200000/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_200000/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:ea8dc02b7e36c65ad96f5eb968dd7857e6310784e2d518dd033c1413a9248d8d
|
3 |
+
size 1856
|
checkpoint_200000/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_200000/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 sha256:74a28bf1517eed54abd95c38495a8d44fa9233e51b1eb465090478084bdbfc69
|
3 |
+
size 1823
|
checkpoint_200000/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_200000/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 sha256:8aee58a31fd9a1cdbe2d37e683fa6c4d90933bf60619cf07a3ae27f57eb6ed07
|
3 |
+
size 1852
|
checkpoint_200000/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_200000/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 sha256:9328340622b0fb99fe3a0712a8f3708be438ee7b29c45e6854f33b9ffc5018f2
|
3 |
+
size 1875
|
checkpoint_200000/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_200000/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 sha256:3bb40c018e12d4e679d5dea593b7ed53fabf6f620145b0a3c8239ca0250b4fe4
|
3 |
+
size 1819
|
checkpoint_200000/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_200000/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 sha256:9468d4e9b7f2e43ffb0c6f78a8ea02d2c19d5bdd8b2ecc2679ac98229a820494
|
3 |
+
size 1859
|
checkpoint_200000/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_200000/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:e72970be62eb1e7b004b39ee5a8a897338745cba99d43e36fb348db49d41a3d4
|
3 |
+
size 1855
|
checkpoint_200000/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_200000/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 sha256:76a906b81ef3b33c4b6d6edcfeb9d43a9b1571e7eeefdeaedead77c2ca3327b5
|
3 |
+
size 1816
|
checkpoint_200000/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_200000/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:fc6f0186026e692d2288c15fa61b3d7272ead19c97df5935982a0851dd721e58
|
3 |
+
size 1832
|
checkpoint_200000/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_200000/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 sha256:840b06bbbfe148410ce5d45c93e0040aee3b37769b7c610b85a895394db79986
|
3 |
+
size 1885
|
checkpoint_200000/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_200000/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 sha256:3b7cea193a74ba65458569d9ecb57ba3e82e4b1a259282b379a3d6e7ca290c8c
|
3 |
+
size 1814
|
checkpoint_200000/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
|