Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +32 -0
- per_head/layer_0_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_0_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_10_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_10_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_11_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_11_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_12_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_12_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_13_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_13_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_14_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_14_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_15_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_15_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_16_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_16_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_17_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_17_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_18_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_18_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_19_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_19_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_1_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_1_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_20_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_20_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_21_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_21_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_22_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_22_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_23_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_23_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_24_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_24_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_25_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_25_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_26_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_26_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_27_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_27_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_28_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_28_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_29_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_29_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_2_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_2_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_30_per_head_simulated_rope_qk_dot_product.pdf +3 -0
- per_head/layer_30_per_head_simulated_rope_qk_dot_product.svg +0 -0
- per_head/layer_31_per_head_simulated_rope_qk_dot_product.pdf +3 -0
.gitattributes
CHANGED
|
@@ -92,3 +92,35 @@ layer_6_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs
|
|
| 92 |
layer_7_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 93 |
layer_8_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 94 |
layer_9_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
layer_7_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 93 |
layer_8_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 94 |
layer_9_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 95 |
+
per_head/layer_0_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 96 |
+
per_head/layer_10_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 97 |
+
per_head/layer_11_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 98 |
+
per_head/layer_12_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 99 |
+
per_head/layer_13_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 100 |
+
per_head/layer_14_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 101 |
+
per_head/layer_15_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 102 |
+
per_head/layer_16_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 103 |
+
per_head/layer_17_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 104 |
+
per_head/layer_18_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 105 |
+
per_head/layer_19_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 106 |
+
per_head/layer_1_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 107 |
+
per_head/layer_20_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 108 |
+
per_head/layer_21_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 109 |
+
per_head/layer_22_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 110 |
+
per_head/layer_23_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 111 |
+
per_head/layer_24_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 112 |
+
per_head/layer_25_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 113 |
+
per_head/layer_26_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 114 |
+
per_head/layer_27_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 115 |
+
per_head/layer_28_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 116 |
+
per_head/layer_29_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 117 |
+
per_head/layer_2_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 118 |
+
per_head/layer_30_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 119 |
+
per_head/layer_31_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 120 |
+
per_head/layer_3_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 121 |
+
per_head/layer_4_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 122 |
+
per_head/layer_5_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 123 |
+
per_head/layer_6_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 124 |
+
per_head/layer_7_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 125 |
+
per_head/layer_8_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
| 126 |
+
per_head/layer_9_per_head_simulated_rope_qk_dot_product.pdf filter=lfs diff=lfs merge=lfs -text
|
per_head/layer_0_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98c967999e64de56c747e7b26a469f4bd8965d2ae68bcd4ad69174a51e2169dc
|
| 3 |
+
size 589669
|
per_head/layer_0_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_10_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b72de1bbba3357dafbe4b98c2b3f6464877a8450d0fd237f4171ac7d167e6a3a
|
| 3 |
+
size 516573
|
per_head/layer_10_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_11_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:892f891681ab9310626097136e8c2dd4514815db7734eae9a43ab1d424614a7b
|
| 3 |
+
size 516384
|
per_head/layer_11_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_12_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a572deceadb0ac120c6dc71d8b5b9e849e95e42b21b837a860f93034be8f4128
|
| 3 |
+
size 507643
|
per_head/layer_12_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_13_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e382645e1f914b1120c42d484c58b6cdac382477bbdac48372b9ef285ed5fbe
|
| 3 |
+
size 512121
|
per_head/layer_13_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_14_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2865f99407091fa166106a23d4acbea962eeb217bdd02e98719af22af64b9905
|
| 3 |
+
size 524999
|
per_head/layer_14_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_15_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c94951d706800b03fcafc1cd1a84acbf5c79dceff629d0242f5668e2ae59950c
|
| 3 |
+
size 506529
|
per_head/layer_15_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_16_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d66744802fc79d632f9bb2e9cc56ba2b0ff7a56a72acf1c353f9ddf0ee370010
|
| 3 |
+
size 515531
|
per_head/layer_16_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_17_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acb56272a1387c3bb9cfac4ca67dd9dfb9dd4bb1b5d0e1a78d6cb26bbeeeea23
|
| 3 |
+
size 521007
|
per_head/layer_17_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_18_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c27c5eab349e55663297ced68f9b59494eaf1c98b0a162422824e493742678d1
|
| 3 |
+
size 511604
|
per_head/layer_18_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_19_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec6e8c6f34e2517bbf5d74bcfdb50edae554ff80240c211694cf53fe4aed6105
|
| 3 |
+
size 501046
|
per_head/layer_19_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_1_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93dc6bb8a3c1116d35362869029abfbee3bf41223bd94dd8a9f49ce3eb12b7bf
|
| 3 |
+
size 574997
|
per_head/layer_1_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_20_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13fd83a420e14358dafc8abfa7c1b4bb7864ddad1ac6a8969faaab99aa07b1c6
|
| 3 |
+
size 508889
|
per_head/layer_20_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_21_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eafb9d463ae713fb54d80ce51ca111677fc5127891356345855fc562bbba4ea6
|
| 3 |
+
size 490202
|
per_head/layer_21_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_22_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32817aafb585ca675e2dae6521ea7317aff204b7c8b50b0a98a1b9fbf22c27dc
|
| 3 |
+
size 507963
|
per_head/layer_22_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_23_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a6679bec2ebf19e2a77f404cd3124b97a6d8a4f9c1fe65d90d132debc6ec275
|
| 3 |
+
size 511343
|
per_head/layer_23_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_24_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a2c9fc7d56b11b2034fa9bc074eb22c597366dd1411e8a0b898b0446956f6e5
|
| 3 |
+
size 490672
|
per_head/layer_24_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_25_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c303da3c8caca21a6e826f29a6187ee4388ee249bdb8f031b968b5d02b84e4b9
|
| 3 |
+
size 520584
|
per_head/layer_25_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_26_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38d7ea8cdc345e33cbcc56c95ba7320b7dad81a0121052e6910a9be6edd15483
|
| 3 |
+
size 528060
|
per_head/layer_26_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_27_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b38f8ccd06c82300b7c74551613dfe120e010599669a887742412cb955fc8cad
|
| 3 |
+
size 528055
|
per_head/layer_27_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_28_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3852ab0bfc8c5a9cee00511a4497ce369a77a3c1272b7f10a6abe98b90ecf51b
|
| 3 |
+
size 529550
|
per_head/layer_28_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_29_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a6226fc055370d0090442b8b27b03d1a30a281ac9ab2974e4e9cfb83aea8cc3
|
| 3 |
+
size 541018
|
per_head/layer_29_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_2_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f716fe7f7b9dbbbca1402673db0b868645ba204cd2a5b50a49f32f6b714e24e
|
| 3 |
+
size 564481
|
per_head/layer_2_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_30_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63575f914309848cbf04e9109c3e0ee12bead5867e439193bafc442bfa25e371
|
| 3 |
+
size 546322
|
per_head/layer_30_per_head_simulated_rope_qk_dot_product.svg
ADDED
|
|
per_head/layer_31_per_head_simulated_rope_qk_dot_product.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd8c7b0a68d465e9b22b116b19e085eb431eee061e50912440f264f1e92b2eae
|
| 3 |
+
size 559981
|