diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/1-10000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/1-10000000.json.zip
deleted file mode 100644
index f320cfc939d22666c4a4a936ec897a8f09227ea8..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/1-10000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:933dd8c12084aa5e7e766c91bcc94b8a8cd93ed9fea28f0e72da298256975079
-size 82618568
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/100000001-110000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/100000001-110000000.json.zip
deleted file mode 100644
index 29d49391f8c304a2d6eb042b20fb6ff14cd79111..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/100000001-110000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:285cc20535c9e72b76e669a933ce41837d4e83e9693266a553ab854bc1be2623
-size 83563457
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/10000001-20000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/10000001-20000000.json.zip
deleted file mode 100644
index ca22e93ceaf941942c36eda50fedc39756b497d6..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/10000001-20000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7ee621e4bf3e6bc7195971aa8c3e6672da297d4a235ad5744c052a6f6e702d6f
-size 82651179
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/110000001-120000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/110000001-120000000.json.zip
deleted file mode 100644
index 9a455ec252b498c8799f8d0bf41068150333ab42..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/110000001-120000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9529825c0a370f461948b403022362d263c011ec55e62dd88c04ad7e4932578a
-size 83606583
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/120000001-130000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/120000001-130000000.json.zip
deleted file mode 100644
index 6e379a02b3d11e9494f0fe6b30350f7a69b7373f..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/120000001-130000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6ffc55e085c961de55be7d68350f20ef4aa59f8ef5aef3ceca5d227a1d2d113d
-size 83598821
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/130000001-140000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/130000001-140000000.json.zip
deleted file mode 100644
index 981f43c0a1e916095d37ddf23a81d51f277e0739..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/130000001-140000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ae32c7f988d257388794449371476b1cb4277d8433c3f2d9d4cb28ec968d5986
-size 83660007
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/140000001-150000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/140000001-150000000.json.zip
deleted file mode 100644
index 686a540c9ed1945eb5229532e1741d9279705296..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/140000001-150000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f9c3842bfca33433d3285df2ddc2eaf9e4fe8783d94c9be78c3895797e2b1193
-size 83656259
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/150000001-160000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/150000001-160000000.json.zip
deleted file mode 100644
index b14b026cef3e76760b201277f4cdecd9a777c21a..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/150000001-160000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f4edbb246c16ddda89eae807af9eb6b4e35c20f936c49039d19c089e6812293a
-size 82971402
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/160000001-170000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/160000001-170000000.json.zip
deleted file mode 100644
index 9449c206fefe3048f7a11433a7a8ac338a93aac4..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/160000001-170000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1b3971f04671e329812a84fd82b7c2404e4851b397d51ff9d75f45c18ca898e0
-size 83011653
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/170000001-180000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/170000001-180000000.json.zip
deleted file mode 100644
index 1957ac7c8a539bfea974753afd9dfd63f873948e..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/170000001-180000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:629a583a3b5016b1b0eaa1456ac78750cf1c702d6fcdd1627506c76f30b95be3
-size 83079891
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/180000001-190000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/180000001-190000000.json.zip
deleted file mode 100644
index 4141bec0f67a9af3df55151109c2bddfc9d98952..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/180000001-190000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2e4dd38290ed2b58492a89d1e4e8275d8dfa5b4e885e1bc839fbe03d7251b9f9
-size 83107396
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/190000001-198951378.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/190000001-198951378.json.zip
deleted file mode 100644
index 12ca491ca1c9f243659f89cab12e01f7403e5b26..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/190000001-198951378.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f1bd09b0b7ad6d5f22b7102b48b1a51bc8222454e463a4e243fe2789b0e33c7c
-size 74583876
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/20000001-30000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/20000001-30000000.json.zip
deleted file mode 100644
index 70ceb469706fad174443942a89c4e461a48e7e43..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/20000001-30000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:07f598a8e4269345817c8d6010c98eb61d4b54c383ff72baea32f5b31eb3d646
-size 83329818
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/30000001-40000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/30000001-40000000.json.zip
deleted file mode 100644
index adc2afae09d73686d43e052ddf16545bb986d373..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/30000001-40000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6ea3e0d19f3957aa71070f1cf79b0f7bdbcf974a3aa3ee1941b0cebcf2489ebf
-size 83254010
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/40000001-50000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/40000001-50000000.json.zip
deleted file mode 100644
index cf2e925fda02dac76be227eafbdfe23910813363..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/40000001-50000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f6d683e4effec06d95effe55a82a9f089c1c29446121f1aa4bd9842637a95af7
-size 83422331
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/50000001-60000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/50000001-60000000.json.zip
deleted file mode 100644
index 9e438d43bc12119f98ad7b987ce920f3952fae28..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/50000001-60000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4b9f39c286497216a9adca902046dadae2cafb3e92166b9a3065f1f97888f6a2
-size 83447844
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/60000001-70000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/60000001-70000000.json.zip
deleted file mode 100644
index 4abb04035495ef3ed5c236a04f128d93c456c9b1..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/60000001-70000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:83c14b29ad6315f3705ee19588d9febe51aef34b48774e6dd169332643375b28
-size 83342886
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/70000001-80000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/70000001-80000000.json.zip
deleted file mode 100644
index 0f58bd6520506cb4beb0a587c6def7831b8c0fa5..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/70000001-80000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:19b2dd442958cd2f474a3bf43e6b03c2cd958ff335dfcba55c17dbe31938bb19
-size 83363633
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/80000001-90000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/80000001-90000000.json.zip
deleted file mode 100644
index 3c4019db29cd42fe59e6280fa0122aa0e4163098..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/80000001-90000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b56354fccb29c5c81d912831f5c819dcd9fe3f12f41a0854eabf7f72a5308ae8
-size 83438438
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/90000001-100000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/90000001-100000000.json.zip
deleted file mode 100644
index 6054021d60b9f875f3d1695a25396ffaa67c5d89..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_vectors_column.json.zip.chunks/90000001-100000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:84b373e57af4a7d02757f6bfdbba41a7f5bf9e216ad2fa040573c551671bb2a9
-size 83404889
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip
deleted file mode 100644
index 99636accc67e155416476c09b6cf408e72ce883a..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b8e0fcc1730f889a2e91a14a62560100ccadea1267906abcf5f8e87fd0c1c816
-size 1657567997
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/1-10000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/1-10000000.json.zip
deleted file mode 100644
index dcb21acd519cddc3b49df3a7e72cea6589eec41d..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/1-10000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a9d1bd81c022f68ba6abab5a99c11f81af5f4c76e807342f5659b14b31d0ea83
-size 82635654
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/100000001-110000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/100000001-110000000.json.zip
deleted file mode 100644
index 19ba097e0b115c274d015fb106510384317db576..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/100000001-110000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ad7b5915b20e039f5c37381ce3d5ec4e97c0961e018d9573ed99b3effb2fc48d
-size 83585961
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/10000001-20000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/10000001-20000000.json.zip
deleted file mode 100644
index 89494e116115f74a1434380a8caf4e329867bbb8..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/10000001-20000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:585504a2267837e47a590e4611811629c01037d77e726f5ad90ea64c290ac1f7
-size 82674087
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/110000001-120000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/110000001-120000000.json.zip
deleted file mode 100644
index b1f6366d17ff9908418c465f4de2f5df42c06167..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/110000001-120000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0fbf058d83d34decfe2563a7cab9f4457ff566e8c301dfe710a461d8a94625d7
-size 83632748
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/120000001-130000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/120000001-130000000.json.zip
deleted file mode 100644
index 9254855675349a145405b64842b5e75bf2f82e39..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/120000001-130000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2a318cb42db7942501e3b4a8219cf40d47cd38ca2893d818ef9fae15351eb36d
-size 83631013
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/130000001-140000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/130000001-140000000.json.zip
deleted file mode 100644
index a55f974a8558173048c04a32f043c733e812e072..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/130000001-140000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f3398c3c545d96d873cdd67d5e0e020d2ab7ed585351850b135f211b0087fe90
-size 83678404
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/140000001-150000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/140000001-150000000.json.zip
deleted file mode 100644
index bd2cd25a125b71a895d0d5b41e7f42fc24543f2d..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/140000001-150000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d859c9670370b8668e6af8ca7a4cf3b1e98269bd03a5cc2afb7f68bad7b4886b
-size 83682682
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/150000001-160000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/150000001-160000000.json.zip
deleted file mode 100644
index aeeb5689a2fb1edfc13aad810dad394db34f1b2e..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/150000001-160000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d4f8aa7865afd686a008919c3b87ee1c34061b541966f6640b9714a44a40938e
-size 82992067
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/160000001-170000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/160000001-170000000.json.zip
deleted file mode 100644
index d425b384cca4a5c7d0734380e51477b77e3e5e02..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/160000001-170000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a573a4952fb0eb1c2b94bf4e251cc6d3ba54b4fdbc6720020d27c25b852366b9
-size 83030176
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/170000001-180000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/170000001-180000000.json.zip
deleted file mode 100644
index 66aa16cda24d19180759e17e92355ceaab413fa4..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/170000001-180000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:906d0f63ac82c911d9ab7a4b03b01c311ec73471fdc4a5abff1a5be99a817255
-size 83111370
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/180000001-190000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/180000001-190000000.json.zip
deleted file mode 100644
index 6c523e7201de5baeb47e280cd46e8a4b0901f63f..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/180000001-190000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:96b95da5069702fece8eb9f50a8ca910f8ab6f782f84671044e2d983109d2b67
-size 83124572
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/190000001-198951378.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/190000001-198951378.json.zip
deleted file mode 100644
index ccbbe7140946cf2becddba6ad4f57c6a18a7a682..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/190000001-198951378.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:726eea24ef3d1d3ab120686d61d81ba0be1b2e40d03eba317012becc31538493
-size 74605953
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/20000001-30000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/20000001-30000000.json.zip
deleted file mode 100644
index 5465680a61c5dc58c2ea587e861873ae4f32c013..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/20000001-30000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b2b1b91c716ba9b2fc3046dfd9c00ca8967a38a4989d49f2fe7d94548619d919
-size 83349929
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/30000001-40000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/30000001-40000000.json.zip
deleted file mode 100644
index 9f962c172294a31da5fd5a0b4c15c77f161bfe58..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/30000001-40000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:328d080a37aa3efc8c50f1c2bdb45182983958741059dd6d2d21ede62e7033f7
-size 83274857
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/40000001-50000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/40000001-50000000.json.zip
deleted file mode 100644
index cb6bf4e4af45528b75a20591c87330b58c765627..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/40000001-50000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:508d112c938b1b6d46abef6d7dce00073eb5bea8a63e778a2fbcb5ceb625d00c
-size 83447527
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/50000001-60000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/50000001-60000000.json.zip
deleted file mode 100644
index afe7026cbaa90e206af4492b93af527aa70878fc..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/50000001-60000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:647420fc818fb4db1c8f9660bacefd6162067b3a37182697bcfea5aaac444a94
-size 83471561
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/60000001-70000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/60000001-70000000.json.zip
deleted file mode 100644
index 45eba43d92373359053232a42aa0188938cd1fa0..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/60000001-70000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d495c94413c0d4789e556dffbbcd729fd34d6df20689ef33dd07f9151f99a734
-size 83365347
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/70000001-80000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/70000001-80000000.json.zip
deleted file mode 100644
index f1a6a75e3071216514db38b7d7d9806373a31459..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/70000001-80000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f170374c634e53c4877b501a3008149e0273a64c0909db1e3ea33e9bd854329f
-size 83387039
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/80000001-90000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/80000001-90000000.json.zip
deleted file mode 100644
index 25d8fea4f49fd2006eb55daf20ec9462f14ae7db..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/80000001-90000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:366b73d49e87b05d2f74dbeb4850c3039b70ec95fa1b153ac12f7903799326f0
-size 83464449
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/90000001-100000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/90000001-100000000.json.zip
deleted file mode 100644
index 5431a3704dad56c6d91c72933c2aa0435ef2834b..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/reduced_weighted_vectors_column.json.zip.chunks/90000001-100000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0c1f543c63f4f18a5d3d95fd60847a717bdf3ba6c15c88323ab4f445161d781b
-size 83429808
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip
deleted file mode 100644
index 59f5ad9d4dec56e555dd58f20d8499d251067d77..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7836527e0491d40b9ae4f75a455c7e49123976df3979d4aa1f527ef93838d8a9
-size 1657429194
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/1-10000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/1-10000000.json.zip
deleted file mode 100644
index 56c2669baafef7396fcedabe311b695dd07b7537..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/1-10000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a8ff2d2b126e0affe8df15a6a1ce5ccb906cc4ff54438761b36baf4256a199c2
-size 82648201
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/100000001-110000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/100000001-110000000.json.zip
deleted file mode 100644
index 929ee699cf9482bebb5c6e08621298ad54841b44..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/100000001-110000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aac4588fa1b0b810238691fda74652001c7f02d8a7aa369f96b09b21e3e9a11e
-size 83554248
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/10000001-20000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/10000001-20000000.json.zip
deleted file mode 100644
index b2a80ea63f64c448e1fa833226a5bb32a11e6f3d..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/10000001-20000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c13dcaff4e9ec675aeec00ecaeae55c3c35802c78e6d958fb6f4a1a0bcb4bdcb
-size 82713474
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/110000001-120000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/110000001-120000000.json.zip
deleted file mode 100644
index 3d976fb9d92e273247e58b9623ac22518609fafa..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/110000001-120000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:de22b04187bde275cefaea030a0f042a90b155fde341c3760a0d679da3be8eec
-size 83617675
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/120000001-130000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/120000001-130000000.json.zip
deleted file mode 100644
index 79889c3276d3b8ddef251a8ecc01ff475c8ca11c..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/120000001-130000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:834e245b50883fbc7b583e1faa5f9d4bce1ed6bc6cf519a8bf394e98b9395820
-size 83630788
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/130000001-140000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/130000001-140000000.json.zip
deleted file mode 100644
index 70bfcbdcab3641f5cc51323dbe93a20c5f39a209..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/130000001-140000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a9981c1a8d7568a462f60e32b1cb1aac50dc9568d23d5c07f4341cf0a922d3c2
-size 83652320
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/140000001-150000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/140000001-150000000.json.zip
deleted file mode 100644
index 849c46dd05964e7d7a4971909b0224d0ea19e869..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/140000001-150000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:41da02379273dbae787f4accaf83442b9bace163eed2c148cf7f0d6e52df71ff
-size 83698986
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/150000001-160000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/150000001-160000000.json.zip
deleted file mode 100644
index f615379928489a2250a6dea038c9e2150cf13751..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/150000001-160000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:010b2018becff5f9ab0c0c56bc9343e53956f163597ac32b4a7a40b31674545c
-size 82986688
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/160000001-170000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/160000001-170000000.json.zip
deleted file mode 100644
index 5634dff76662f76289c16b11f38231ec9a3481de..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/160000001-170000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d34399adc547caa5c8e7fe55b01d52aeb40c5ca881502448a561873ea2446056
-size 83011165
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/170000001-180000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/170000001-180000000.json.zip
deleted file mode 100644
index 21d1a40235eae6264c3099e2edae7bb23cccd8f0..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/170000001-180000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9837610e1c6d47d75f40daf1acf2e9c83541b585690796c628b4e19e4af673f8
-size 83050557
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/180000001-190000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/180000001-190000000.json.zip
deleted file mode 100644
index 576c9c6cfd53c32fc6bdb446d4b34225c791dfe5..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/180000001-190000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:76f918b7484e53b879b427eaa5f819f7ca3751e5999b75e192aa79167cf114ec
-size 83130574
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/190000001-198951378.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/190000001-198951378.json.zip
deleted file mode 100644
index e986da998faf6dbaf6f5af5f5d318c8b9a0e6fba..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/190000001-198951378.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a371ca08f01973b56f98652480475943179bc1454836a342fc7a32a2f3efd40d
-size 74607899
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/20000001-30000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/20000001-30000000.json.zip
deleted file mode 100644
index ed7cafe0e5584a0218f47cf2c22b4a15df5cac65..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/20000001-30000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a3d5386dadd0818404a2bd39da5dc2eb174e0b6e0a1e17e571918752a1753f40
-size 83320523
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/30000001-40000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/30000001-40000000.json.zip
deleted file mode 100644
index 078b64787112c6c8db6a5ab64182fe136bcc7002..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/30000001-40000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4094487da3e0dca37f9df219c034c4edcd77cd092c9c3e2105c032ddce4d3a15
-size 83331815
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/40000001-50000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/40000001-50000000.json.zip
deleted file mode 100644
index d58edfef7b34ba232ea00777485b0dff15af4a75..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/40000001-50000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:028cb024a05eb6c2a846024fcd181155d8dab4cd9fd0307530c7c701378b877a
-size 83439541
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/50000001-60000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/50000001-60000000.json.zip
deleted file mode 100644
index e7fff618a3de1f9cc7cdff2cc25f81dce1cf0db4..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/50000001-60000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ad50dd203358b54cd078420b00696efdfc3abc91b0138c9eb95ee4938a8957a1
-size 83464565
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/60000001-70000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/60000001-70000000.json.zip
deleted file mode 100644
index 0341ca71bae9069a2173357518ff1422af96f2f9..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/60000001-70000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:32a91001c8af6f8ce5edbfee3c1afcf587c5f419216b5de34b41913b6bdb1985
-size 83310086
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/70000001-80000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/70000001-80000000.json.zip
deleted file mode 100644
index 378ae00760e3b76b3e7bde0af8faf2f607dd81d0..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/70000001-80000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:37e67091c271f02d1f45a33d50b49d92a856276f4f8a0877428d8cbe37c9847b
-size 83392470
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/80000001-90000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/80000001-90000000.json.zip
deleted file mode 100644
index ebe6b3443e04cd612b867bc2bb33ba79c63c0b85..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/80000001-90000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7831a80cd80cc6c1919eeca376aea15110dc005d8ddfcf60fbd3e088c386bce6
-size 83455958
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/90000001-100000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/90000001-100000000.json.zip
deleted file mode 100644
index ba56ce7c5c8c45c8d1b29cd6febc089e91a0c256..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/vectors_column.json.zip.chunks/90000001-100000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5d9ba42286ffafcfd11ffd6ce4561bc6e87ee21d3e955b3f7c3d5aebc294d0fb
-size 83418627
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/1-10000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/1-10000000.json.zip
deleted file mode 100644
index 06d205a03b5e0ec81a44e87d636441a687137562..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/1-10000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fa6513198ff7f083276d76b75795d32d4b4fccf88419c9547f62e90c327b2ae4
-size 83312932
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/100000001-110000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/100000001-110000000.json.zip
deleted file mode 100644
index 2b60da56c2a695ea8adb642d09601725d3e06f8f..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/100000001-110000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9a41bfd43e266f47d9c4c9958a00872117675b15b1e6b712689dbdd618fdcc17
-size 84231880
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/10000001-20000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/10000001-20000000.json.zip
deleted file mode 100644
index 40b9fc96b02fd00583fc81305980aa9b4d3a3e1d..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/10000001-20000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7b2f0724f392b6c7184e84be5c623230811aee99dd3cf59e7c415971c567d632
-size 83345473
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/110000001-120000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/110000001-120000000.json.zip
deleted file mode 100644
index 59238b1c8a189e797e2a0b0ba4364c3972dfa261..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/110000001-120000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f0473d96699cff96d0cda5635731866d8af25e447751402e11090d50751ab27b
-size 84271156
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/120000001-130000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/120000001-130000000.json.zip
deleted file mode 100644
index 41c6d9e2b01a6a6b2444c105872af747a9258e11..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/120000001-130000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3bfee45a0303004380a51373afb6565dc0af10bda92e89d0db5cff41a624c5df
-size 84308923
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/130000001-140000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/130000001-140000000.json.zip
deleted file mode 100644
index 0f8c9ec61c0093a5e2ec14639b51305dfc436072..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/130000001-140000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9a4842d8c4e0cb7ee9c84720ca98ee56783a6555fe2f887ecb90adacac5ee59c
-size 84340350
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/140000001-150000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/140000001-150000000.json.zip
deleted file mode 100644
index d446c2c947a6477dd0ad8524455131c861a1c563..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/140000001-150000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4a1cf858c03ed511adebb83d2df6a3400921362e411364801576e7bc0ca20199
-size 84332177
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/150000001-160000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/150000001-160000000.json.zip
deleted file mode 100644
index 3c6c77db531945a9072b683915945256e01eb6f1..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/150000001-160000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:352d5623d001799f1c4757abab4e5e3faf99eee8ce101d7edcc2678cb0bd71e4
-size 83640427
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/160000001-170000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/160000001-170000000.json.zip
deleted file mode 100644
index 2df0081d1b939e3c629aeea2fddaa018b92b1b57..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/160000001-170000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:36068892dbd29c87cb35f259fb0c5d266cf847c69fe1c1572466e2644e032c7c
-size 83672129
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/170000001-180000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/170000001-180000000.json.zip
deleted file mode 100644
index b84945936619780c3954f4a9fa909392b1b8a3f1..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/170000001-180000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b514ab8bfad80dc9ba2e28e994d868abd8717b13f7bd7f8c7d7adc56dc89ca43
-size 83714736
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/180000001-190000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/180000001-190000000.json.zip
deleted file mode 100644
index 073a0158b0d31b4cb7988194d1292557e4453361..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/180000001-190000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6af2a9c3a73ad447f1f21b81b36909634e3437735f2c95423980ca9c67885bdd
-size 83773762
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/190000001-198951378.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/190000001-198951378.json.zip
deleted file mode 100644
index 1f08e5208969b412f4ca0ca2190a3b725ab12b02..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/190000001-198951378.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ca0a8c5be72238d69e6a07ca35124ca4e2f013639c1cd94fdd0be77622321e4a
-size 75201126
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/20000001-30000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/20000001-30000000.json.zip
deleted file mode 100644
index f0d4654d44a37a12bdd53251f2683eeefa7929d0..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/20000001-30000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:73bf0df88362a47d552c2f448d2150ae19fe77c1f573ef8abf782f80f0034c0d
-size 83993027
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/30000001-40000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/30000001-40000000.json.zip
deleted file mode 100644
index 0cb66cfb8e7216c00190180ccdc851049cc484c9..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/30000001-40000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:81c8cd103257d9c9bc69245f498f88735e58b43b2357098c960acef24a7afe29
-size 83997832
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/40000001-50000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/40000001-50000000.json.zip
deleted file mode 100644
index c40519112559660641f6fb19b740ef61ba350f51..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/40000001-50000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:01650eb219a2f93c9f58d7204d6854fea04a276b8c9ad2d4e8167739711e07d8
-size 84089981
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/50000001-60000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/50000001-60000000.json.zip
deleted file mode 100644
index 9cf1959844eab044cd336e0b449208545cf55457..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/50000001-60000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1e6616ca154631388b61a34d8538db211f55248cea022dcef3a68b64e91e4599
-size 84112416
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/60000001-70000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/60000001-70000000.json.zip
deleted file mode 100644
index 7b7d4004592ce0580f1af79894fe40c0b7915c86..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/60000001-70000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f1e48998f87c738dbc9b62e295c5400820015e7ab57006986400d01ddee9d3c4
-size 84017804
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/70000001-80000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/70000001-80000000.json.zip
deleted file mode 100644
index f4ff52d69485e7a9555864b2f86070775d693d9a..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/70000001-80000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d248aabd234c4c027bfb4f8b74087630f49c810914f5ca5ce69380ec21d1fc26
-size 84050024
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/80000001-90000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/80000001-90000000.json.zip
deleted file mode 100644
index 9a4f3d95c2eb5c1c2a549a7acd6aa20eca40cf33..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/80000001-90000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3ca205b90d4eb18877eb51262ed85fe76a70de2fd753dfdbdd56466616eda06d
-size 84123293
diff --git a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/90000001-100000000.json.zip b/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/90000001-100000000.json.zip
deleted file mode 100644
index f79bf730531c5fad4638159617d8755f56b26647..0000000000000000000000000000000000000000
--- a/data/processed/RVL-CDIP-invoice/cosine_similarity_scores/weighted_vectors_column.json.zip.chunks/90000001-100000000.json.zip
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4990192b22be4f1de98964750453e3a0c553a23c1d39f56324208abdbcf2d3b8
-size 84113092