diff --git a/full_data/c4/part-00-00001.csv.gz b/full_data/c4/part-00-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..142a1f881fbf75b98c4d9424bdff3acef5bf5d06
--- /dev/null
+++ b/full_data/c4/part-00-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb135101b41b9dfc32a446380465db248285471c6a4137424ac5c1b20652a764
+size 62004259
diff --git a/full_data/c4/part-00-00001.npy b/full_data/c4/part-00-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..fc8bbf538eaa6d137a5317781b821727be5de244
--- /dev/null
+++ b/full_data/c4/part-00-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d02d5c81b168cc2a9542e347a34ea4749510bc5cf8b1084f5ca98f25bf3265
+size 1957542958
diff --git a/full_data/c4/part-01-00000.csv.gz b/full_data/c4/part-01-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..8ee593302debfeee4aaeaef29874166b4b240a93
--- /dev/null
+++ b/full_data/c4/part-01-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ead6c0d8742bcc06902ed2b42ea3f62491af2b80ca882c5013430b26448c9420
+size 67993304
diff --git a/full_data/c4/part-01-00000.npy b/full_data/c4/part-01-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..5dedd5a5029e22223c8a0ac7c22d783f9035152b
--- /dev/null
+++ b/full_data/c4/part-01-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:820d35945363f47d9300d42308b3fd8b24b3701368fe846e2d714a33583a86be
+size 2147482402
diff --git a/full_data/c4/part-01-00001.csv.gz b/full_data/c4/part-01-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..66c548b289a7799c45ccbf91b5e7a83f6e1edd82
--- /dev/null
+++ b/full_data/c4/part-01-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f4acdb47b4e948ccbc452e9161db88491ce17b15683e5bf9a8911e26592267
+size 61846986
diff --git a/full_data/c4/part-01-00001.npy b/full_data/c4/part-01-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..65a65a87e7c754fa2e555d66053b677614b2e136
--- /dev/null
+++ b/full_data/c4/part-01-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8465b63e2b0cb9d4ca731f6ee7d9a4a8e9114e9473a30b30271bffc2c37420cc
+size 1959445232
diff --git a/full_data/c4/part-02-00000.csv.gz b/full_data/c4/part-02-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..864ee04763ba0b97bb7d394bd723d5ae4ddde111
--- /dev/null
+++ b/full_data/c4/part-02-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d3b28469730b823b12423eb40f3996dc01a36f0ce3c6fb494f2c79f754ef06
+size 68138791
diff --git a/full_data/c4/part-02-00000.npy b/full_data/c4/part-02-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..25e4dacc6f8b3e70dd44830f9b60b50854cc225c
--- /dev/null
+++ b/full_data/c4/part-02-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a6e728e98d5ce73ecb6c3dc321ace4306e68ded42741e2385394298755e3c7
+size 2147483254
diff --git a/full_data/c4/part-02-00001.csv.gz b/full_data/c4/part-02-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..b0325cfdd089760ded8ed6c63529022ceb13ffbe
--- /dev/null
+++ b/full_data/c4/part-02-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e8101c4c1d6246e32a4234deec5c67c1754d8a2e45eeea56b0554eb40bb0db6
+size 68055319
diff --git a/full_data/c4/part-02-00001.npy b/full_data/c4/part-02-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..71ea6128937f32ab3ffa815df5ff4f5241da7a3d
--- /dev/null
+++ b/full_data/c4/part-02-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14bc78e8927e14c01d8b8f403f43b98cd3e47d6236dcf4a34b39ef165c662948
+size 2147482558
diff --git a/full_data/c4/part-02-00002.csv.gz b/full_data/c4/part-02-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..551e0c7911b3eeab752d1d3917cda3b6f2456ab8
--- /dev/null
+++ b/full_data/c4/part-02-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf5cf202442333e0021f570ed8d9f44abb73cb959b84e7f600874fd174e48b8
+size 68199901
diff --git a/full_data/c4/part-02-00002.npy b/full_data/c4/part-02-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d006e99a03380b0110a47661bc8b7d9f5a95ff66
--- /dev/null
+++ b/full_data/c4/part-02-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f0ae3b687a2adc23f72227c7ee31d8e58bf51ecd1eb963e60a6f40809a5c93e
+size 2147483072
diff --git a/full_data/c4/part-02-00003.csv.gz b/full_data/c4/part-02-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..0335aae86f45c48abd60c7f102b30895c5682827
--- /dev/null
+++ b/full_data/c4/part-02-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431e031a0e80f5bf214b2f0b9894b0939a3b3b23c3a16cc24f8ba705df130a26
+size 55961227
diff --git a/full_data/c4/part-02-00003.npy b/full_data/c4/part-02-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..aef999265d6a7f5bb67a57cdcf611e7646969f84
--- /dev/null
+++ b/full_data/c4/part-02-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e11f1661d4647eb8d4a6f34bf513a3da9eb56a5778d075c3a891bde72099ca
+size 1761890162
diff --git a/full_data/c4/part-03-00000.csv.gz b/full_data/c4/part-03-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..71e3a0497331f9b67f0eaa95f22c1782998c94b0
--- /dev/null
+++ b/full_data/c4/part-03-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2387dca3004a844344371ff6158e5a3399470102ef09a0adf700119023427790
+size 68046053
diff --git a/full_data/c4/part-03-00000.npy b/full_data/c4/part-03-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..7f84a8f965a028d40082731708b396e9736bde34
--- /dev/null
+++ b/full_data/c4/part-03-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad16c6c7bcfaa5cd1c98bbb7bffdfdab260b1475a7b5e0677c377968d96098c7
+size 2147478792
diff --git a/full_data/c4/part-03-00001.csv.gz b/full_data/c4/part-03-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..5e916e05cf8c1b578c6215737315fb250127485b
--- /dev/null
+++ b/full_data/c4/part-03-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d6494401906d3d3a0e15615a9ad281710243e8cbdf7d66210b9e8a5600f0f27
+size 61791330
diff --git a/full_data/c4/part-03-00001.npy b/full_data/c4/part-03-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8b5ad11d9d179d705ac3659cb778e4a3979fdb83
--- /dev/null
+++ b/full_data/c4/part-03-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d693ca2c6cfecad61a9e1bd13f930aee80cae8d0aac91baa01f6fb1b2efedd79
+size 1956181398
diff --git a/full_data/c4/part-04-00000.csv.gz b/full_data/c4/part-04-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..f85ff6661f6bccd425964f5f57afd41f52e98a9d
--- /dev/null
+++ b/full_data/c4/part-04-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eaae66b80f1b3a703bd041549102482dec0e2b8d4739c6edb8dfa937b85d239
+size 68084466
diff --git a/full_data/c4/part-04-00000.npy b/full_data/c4/part-04-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..97895329aefb5262c889545ed521535afc9c20c0
--- /dev/null
+++ b/full_data/c4/part-04-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a38c13888de2034874d09bca4a04d83241632bccb8bb1407eb6601e437ef81d
+size 2147481198
diff --git a/full_data/c4/part-04-00001.csv.gz b/full_data/c4/part-04-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..a0f4a22dee9b36eceae884a32b455f4475654ea5
--- /dev/null
+++ b/full_data/c4/part-04-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc97e332266a662d3220be20051c0e9e12049a6d56d0ba9c2d62a6f0abb1b420
+size 62035678
diff --git a/full_data/c4/part-04-00001.npy b/full_data/c4/part-04-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..fdc6b407c40b09035f1cc0ee24255fd58b258db1
--- /dev/null
+++ b/full_data/c4/part-04-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4507f5ba60027f2fe17c769089cf0f257d6ed96d6882d0d65ca36340037deabd
+size 1957256242
diff --git a/full_data/c4/part-05-00000.csv.gz b/full_data/c4/part-05-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..5e42cac2121a9c532b0fdac8edef78b150e32884
--- /dev/null
+++ b/full_data/c4/part-05-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f89687e68766450465cd4b0293027f3a816b0491335fdc8051d346c647a79905
+size 68056163
diff --git a/full_data/c4/part-05-00000.npy b/full_data/c4/part-05-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..31a6dfea2c19dc228dd40b199e37ebecc41b4ac2
--- /dev/null
+++ b/full_data/c4/part-05-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38e010d75a20fa99fe4674d5c7404001b7d76539e757834e9d1a4b0213496bab
+size 2147480560
diff --git a/full_data/c4/part-05-00001.csv.gz b/full_data/c4/part-05-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e533a2b93029f272e1d12477a845706c1fc62d07
--- /dev/null
+++ b/full_data/c4/part-05-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ca6f01bc6baa720bb7891a4f3182188e2da819787d4d6636ad8f91ed92e899c
+size 68191697
diff --git a/full_data/c4/part-05-00001.npy b/full_data/c4/part-05-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..be0fd83d39138b9d6e2de81b5aae7f13d9c61ff2
--- /dev/null
+++ b/full_data/c4/part-05-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21906c1102a304a1a136ae5d6fecda5ca7bc4055e43541643d626d63b7d8d620
+size 2147481134
diff --git a/full_data/c4/part-05-00002.csv.gz b/full_data/c4/part-05-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..203dd9a1f59e66a341a43b8467e3cba7fc835818
--- /dev/null
+++ b/full_data/c4/part-05-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bfb8b7cf012566fd86580e5c67ea874a4b182f6796d541726989ff4fe7b3697
+size 68052843
diff --git a/full_data/c4/part-05-00002.npy b/full_data/c4/part-05-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..6a158f430a612077a02d392e74b889fec4fb594c
--- /dev/null
+++ b/full_data/c4/part-05-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe149ddb6d294136d994309c545fd32cff695823f981eeba4f768e0c7d5a9e1d
+size 2147477426
diff --git a/full_data/c4/part-05-00003.csv.gz b/full_data/c4/part-05-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..fb9c903b47d929011955631e001afd548be07c22
--- /dev/null
+++ b/full_data/c4/part-05-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8456b36f27a9af97e1f9926bfeb464cc76fa110415bd0e4819c636b5659dbb0f
+size 56052774
diff --git a/full_data/c4/part-05-00003.npy b/full_data/c4/part-05-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..dd85e284a49579fd8e355f73d22d43ea54c311c5
--- /dev/null
+++ b/full_data/c4/part-05-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3628e261384869902e250ec096115896c004abfa54e652554f91bd5402350e7c
+size 1771048746
diff --git a/full_data/c4/part-06-00000.csv.gz b/full_data/c4/part-06-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..21254ab5e510a3e6b99af6fca97a4e95af4eea4c
--- /dev/null
+++ b/full_data/c4/part-06-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e84b3c3c4a917f62b1ee4ce23177b942c032c480685e6f5fdbb8abefcddf63
+size 68137203
diff --git a/full_data/c4/part-06-00000.npy b/full_data/c4/part-06-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..6badcb0f6e63712b3df1e178d5d2c30907c3b8df
--- /dev/null
+++ b/full_data/c4/part-06-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc99418abf352318d2bdcf01aac64748a92f63ef2830d61446c0a9e74a40745b
+size 2147483640
diff --git a/full_data/c4/part-06-00001.csv.gz b/full_data/c4/part-06-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..1f13c1fa6a1da0d2d49b4d5325079824b4706d17
--- /dev/null
+++ b/full_data/c4/part-06-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c08ad033e42f22462bd2008d895cd1206473a1368a832a81f9ea2fc4d8d6701e
+size 61979732
diff --git a/full_data/c4/part-06-00001.npy b/full_data/c4/part-06-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a88bb1f12182472f12c0020d4345a43cd7a85939
--- /dev/null
+++ b/full_data/c4/part-06-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15276903b770edb23cd4de4c079e673457a9b31ff8a7bf2912218aed7d98fcca
+size 1951150502
diff --git a/full_data/c4/part-07-00000.csv.gz b/full_data/c4/part-07-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..d2b9ca13c0aaa7589f6099a12a6eafa1c94ed66b
--- /dev/null
+++ b/full_data/c4/part-07-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3edc47ab4fbc8db9d3b4b965242c3b901f5ff654782ab2c1ce6a03096971dd18
+size 68036317
diff --git a/full_data/c4/part-07-00000.npy b/full_data/c4/part-07-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a2fef66e77d2a5411fa51fb333186044a262a185
--- /dev/null
+++ b/full_data/c4/part-07-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f2dd54f5ed4d05404820e6c2d4d915d560d32ede733313855917479185a50da
+size 2147481910
diff --git a/full_data/c4/part-07-00001.csv.gz b/full_data/c4/part-07-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..6ac8c820e379d3d5c83b394a93da113f3d696cce
--- /dev/null
+++ b/full_data/c4/part-07-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b082faec568f803ac139562d0e57642f0584882a2d0016a1919290d7be05c626
+size 62082206
diff --git a/full_data/c4/part-07-00001.npy b/full_data/c4/part-07-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..b50653836a1fd08dda59622bc6a57f6c4090fdb6
--- /dev/null
+++ b/full_data/c4/part-07-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3041487dd4ece83e960268b3710b1b635f02affe580c9ea84448515b3d78d9d5
+size 1959696508
diff --git a/full_data/c4/part-08-00000.csv.gz b/full_data/c4/part-08-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..121e8d8e64f59714db3eaaf8c225ad37a7535aa6
--- /dev/null
+++ b/full_data/c4/part-08-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b7e08d30b9fd5ef9fa15c18ed3bd0c06c023f31eb4963fe6c0369f967e1c0f
+size 68386435
diff --git a/full_data/c4/part-08-00000.npy b/full_data/c4/part-08-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..ceea4adffd781d1109955b4df535f599d208edb8
--- /dev/null
+++ b/full_data/c4/part-08-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96cb6ee6e59e95d5c108634d4e4b95c103d5b416b615970515b013e6bafbab31
+size 2147482294
diff --git a/full_data/c4/part-08-00001.csv.gz b/full_data/c4/part-08-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..b4f2f562928ef6eda26fbbdd0f01f4a171a804ce
--- /dev/null
+++ b/full_data/c4/part-08-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd6626ab65d1188c1f16211f7e953a6638f2739820c8cf9a476ffb4d9b66afb7
+size 68398783
diff --git a/full_data/c4/part-08-00001.npy b/full_data/c4/part-08-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..5eca0f1ff30a080854a260c14693e0c24cefbf7f
--- /dev/null
+++ b/full_data/c4/part-08-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc15f6c4e45d59016b2a9d9afbacbc32aeed70554a5d6268cf96dc0d6178746
+size 2147482920
diff --git a/full_data/c4/part-08-00002.csv.gz b/full_data/c4/part-08-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..fcc0d796679c631b2d28e2c16629c945f84cca68
--- /dev/null
+++ b/full_data/c4/part-08-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2450cef61628480d86bd59bc917313535bfe9cf0bc26f622b45fffcc0abf7dee
+size 68422471
diff --git a/full_data/c4/part-08-00002.npy b/full_data/c4/part-08-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..66bb6e8894666be91acdea397318af54e1910282
--- /dev/null
+++ b/full_data/c4/part-08-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:855205cc4ea676be2fda9dc2179f693f410bff2ca52d64a7f37c5b19f4d2a250
+size 2147482058
diff --git a/full_data/c4/part-08-00003.csv.gz b/full_data/c4/part-08-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..a28ac65152287b9ec0fc0f8b4e97d8a1b301bd5e
--- /dev/null
+++ b/full_data/c4/part-08-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8ac03ef9d55e315af431383b98d8f2e0855f532ce718e70c6aa6fa9d8fcd8f5
+size 56344118
diff --git a/full_data/c4/part-08-00003.npy b/full_data/c4/part-08-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..770bb007dd147a8682ad79dc621f36756e8fd174
--- /dev/null
+++ b/full_data/c4/part-08-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6057828bde92cbe9b7344ce16fd0193a161e36c183294e201836070786e89e5c
+size 1766517570
diff --git a/full_data/c4/part-09-00000.csv.gz b/full_data/c4/part-09-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..7c465d27e38794425dedd4e60e2f4e68c506e3da
--- /dev/null
+++ b/full_data/c4/part-09-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd073bd8c421b5d55e1403fab533948b39b1d48a2bacffc110f5e0f900c62e7
+size 68004897
diff --git a/full_data/c4/part-09-00000.npy b/full_data/c4/part-09-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3b9dadfbe0e59a89cfb7977fc2a32a8d896dd28a
--- /dev/null
+++ b/full_data/c4/part-09-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9345535f17633437db8763f065da5e36301e6fab042bcc4a55dc2f27dc7bac5
+size 2147466762
diff --git a/full_data/c4/part-09-00001.csv.gz b/full_data/c4/part-09-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..07e060905ed0c240b8edd6488139512d440ae2b0
--- /dev/null
+++ b/full_data/c4/part-09-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:361ea263f0c254bd53dbee2eea341add8a4271ac75772ae569fe81bfd1d1fe80
+size 61829390
diff --git a/full_data/c4/part-09-00001.npy b/full_data/c4/part-09-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d334e722b3fc58e253facf1982a80fdc8e15d043
--- /dev/null
+++ b/full_data/c4/part-09-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:329137004ea6bdb23f2ac5c50a0f5edf24499674320bd614c18d68e70298e64d
+size 1952648730
diff --git a/full_data/c4/part-10-00000.csv.gz b/full_data/c4/part-10-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..aba17ed0b47295c2806d2211db34cc369f9d4450
--- /dev/null
+++ b/full_data/c4/part-10-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761227ff7426a4a1a343aea96fe83924d80fd32ff7ce930033894a7ae321b0fe
+size 68042289
diff --git a/full_data/c4/part-10-00000.npy b/full_data/c4/part-10-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..93df124b31c5afe1f95dbe8298987ad3291df172
--- /dev/null
+++ b/full_data/c4/part-10-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4832d903921e6dbec129e49dd1020690726a9b9408231abc620deee5693538b1
+size 2147483346
diff --git a/full_data/c4/part-10-00001.csv.gz b/full_data/c4/part-10-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..2cf7d6089342ebea2113fdd3350b03208e7e0dd4
--- /dev/null
+++ b/full_data/c4/part-10-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:559dd2cb87d4697ceeab783b57675182d71f592852f28858fc2de84da35b5f8f
+size 62080101
diff --git a/full_data/c4/part-10-00001.npy b/full_data/c4/part-10-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..17c434ecfd161d0e49a5e88edba40ae8c6003462
--- /dev/null
+++ b/full_data/c4/part-10-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3a2fc68c9b3a431085b0df176a0bb2ca88ab730abd9e69605088e5de56395f8
+size 1961226568
diff --git a/full_data/c4/part-11-00000.csv.gz b/full_data/c4/part-11-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..32b2c2c2dcbe7709f6077f84450d523c4e1c91f5
--- /dev/null
+++ b/full_data/c4/part-11-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5281cc1c11c1f11c94e59697a0aa11dff3a943a4dcde86e6fc8d098ec6598bff
+size 68360491
diff --git a/full_data/c4/part-11-00000.npy b/full_data/c4/part-11-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..0996e93817abaa8da398a76ef78e357df58d0f9a
--- /dev/null
+++ b/full_data/c4/part-11-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca8df929a6509c7a3fe13b83828f5c1dbb6def83162f82d9c605f6207bf85554
+size 2147480986
diff --git a/full_data/c4/part-11-00001.csv.gz b/full_data/c4/part-11-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..c685eb10ac170c6c195fbdbf15c0600cefefa7c4
--- /dev/null
+++ b/full_data/c4/part-11-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60c86d6b3b3306cac2033515ad38dd7fc7c8b50b48552b7f35ccda363fc3c5e
+size 68451425
diff --git a/full_data/c4/part-11-00001.npy b/full_data/c4/part-11-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d2901f205c75f14a15f00cf53aad0edd9ca295f7
--- /dev/null
+++ b/full_data/c4/part-11-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7862217b75dacb080564d14658684c9579faafc369fd637f6df97abb3848e638
+size 2147482530
diff --git a/full_data/c4/part-11-00002.csv.gz b/full_data/c4/part-11-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..052a61eb6fcc8b2bfad3ef58dd1b938419bd3604
--- /dev/null
+++ b/full_data/c4/part-11-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:284f554d69f2a7478d6770d1137b517bb3c2a3abe9faaf4ca2ac4d6316c758a1
+size 68480660
diff --git a/full_data/c4/part-11-00002.npy b/full_data/c4/part-11-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..aa399037b4363c133fdb1fc62463e91c90c233ab
--- /dev/null
+++ b/full_data/c4/part-11-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52265d66dd59a736e8abf19d1e30d3504e05a372ce1398bee4794f1c07dec7a6
+size 2147471352
diff --git a/full_data/c4/part-11-00003.csv.gz b/full_data/c4/part-11-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..915dbba4e3380d953565bbd60a0417a6bcf5cbef
--- /dev/null
+++ b/full_data/c4/part-11-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a64354d9d34ecf697b7ef8fb7f24cca8cf529ac9c984f7e2b08e3a0898de1b
+size 56262674
diff --git a/full_data/c4/part-11-00003.npy b/full_data/c4/part-11-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..7717943ccbd21a98232ac92d7b78e8693dfa1eaa
--- /dev/null
+++ b/full_data/c4/part-11-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f94e1358c0255e2715b41b01f847b9b4b92f5f6591afd7a8e8888a38228995a6
+size 1765108552
diff --git a/full_data/c4/part-12-00000.csv.gz b/full_data/c4/part-12-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e104d54f35fe7a02d69e8825de5b74bc9bcc6199
--- /dev/null
+++ b/full_data/c4/part-12-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703b7d05d924060b32b4d4af7a3d6ab6d5f1098249412ef5f2d96e0fcb94666c
+size 68404309
diff --git a/full_data/c4/part-12-00000.npy b/full_data/c4/part-12-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..e8d39aaba47f5d451f1bb90df1b627add22660e5
--- /dev/null
+++ b/full_data/c4/part-12-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c49b8be8bc6af719f5326fc10357edb954d238894c710226fc6a3dd887b8b9
+size 2147482082
diff --git a/full_data/c4/part-12-00001.csv.gz b/full_data/c4/part-12-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..8396f714dfb0661f5ac289b1c55867649f3564fe
--- /dev/null
+++ b/full_data/c4/part-12-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6306665787be4ee9d9b80c7711e9805dbb59f29ecf296b869c0a11b0a6292b2e
+size 62251001
diff --git a/full_data/c4/part-12-00001.npy b/full_data/c4/part-12-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..534a2f4c3e5dbdeee4f2daabff623d945b4f8a42
--- /dev/null
+++ b/full_data/c4/part-12-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f27ab729a09241210f44b965e2af08fe979d57fd790ba7a5aa9cc0f1059dbd3
+size 1958272670
diff --git a/full_data/c4/part-13-00000.csv.gz b/full_data/c4/part-13-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..d95c4374c4561b9ada057a8cd1dc1526fe659af8
--- /dev/null
+++ b/full_data/c4/part-13-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a7a106144130115f55a6cbec7bca26e3cc9341cfa7adc040ca35e5794b48d7
+size 67827115
diff --git a/full_data/c4/part-13-00000.npy b/full_data/c4/part-13-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..b96d51d3ef4a669c6fb6a8ebb114e171c29a31a4
--- /dev/null
+++ b/full_data/c4/part-13-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58259f52a8f2115ea75663879b90117f7a408902f2e5b3ccf76d5ed02c690cb1
+size 2147465362
diff --git a/full_data/c4/part-13-00001.csv.gz b/full_data/c4/part-13-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..9cbc41d06e634f2b3004acbc0ff3fee2ab7caa1f
--- /dev/null
+++ b/full_data/c4/part-13-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:576d39ae6e991d3b94408660b2fdce4461afc496d8ab47aa498783244da8254f
+size 62011593
diff --git a/full_data/c4/part-13-00001.npy b/full_data/c4/part-13-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..404182acd9d14e8d475cf762796b62e94b569b80
--- /dev/null
+++ b/full_data/c4/part-13-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f69d617b1aa259913e677eec98e39447629df33a60920c87fcdb4ab2f1b72816
+size 1959768408
diff --git a/full_data/c4/part-14-00000.csv.gz b/full_data/c4/part-14-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..b4ff2ccec5e7f8f578bcab8db76c37ef9c17c5ba
--- /dev/null
+++ b/full_data/c4/part-14-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7e203546a0ad0069f0658516fe574784a229acb968ae1ee5ebfac7f3c6506c
+size 68179738
diff --git a/full_data/c4/part-14-00000.npy b/full_data/c4/part-14-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3e13524ddaea7b297c2c58e689482516b2020dc2
--- /dev/null
+++ b/full_data/c4/part-14-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72541f514a7686afcb667bc59745ac651fccd0d2b209ad4614db3fa7942d7b62
+size 2147483630
diff --git a/full_data/c4/part-14-00001.csv.gz b/full_data/c4/part-14-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..8eb8c793fb669126408fe014d5e60453ce790175
--- /dev/null
+++ b/full_data/c4/part-14-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:982a26311d8667cf28cd21fa3c813db6d9a7d5d0f42616a4c8d9cf1047eb6452
+size 68057138
diff --git a/full_data/c4/part-14-00001.npy b/full_data/c4/part-14-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..29093f07d9925649d386d95f3cad3440c3b34df2
--- /dev/null
+++ b/full_data/c4/part-14-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9be9d0ae1715b45ef703efdf2f931cdb0f9c0e748c0cbe642a0d353d7585eb15
+size 2147483304
diff --git a/full_data/c4/part-14-00002.csv.gz b/full_data/c4/part-14-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..68b3e5e7205bbd74d64c35b6334702d9829b0de9
--- /dev/null
+++ b/full_data/c4/part-14-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b65af209249e6f85e2832e284df041fc220607695a824bdd6ec793601f7ca2
+size 68063053
diff --git a/full_data/c4/part-14-00002.npy b/full_data/c4/part-14-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..1882280a3be5bac641dd736a6f7c753a0adf05ba
--- /dev/null
+++ b/full_data/c4/part-14-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e1b2fde6e42940f9e3ad5e52739cc25a5c579a35db268d057f07bbff2b7d570
+size 2147481778
diff --git a/full_data/c4/part-14-00003.csv.gz b/full_data/c4/part-14-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..50b18eace0597bd96b2709a41a113a9504ed8273
--- /dev/null
+++ b/full_data/c4/part-14-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8890ef6c2d5dd153d89667bb415abbf7fbe9f16f1e9a74df22ec8e6b589d0cc
+size 56015639
diff --git a/full_data/c4/part-14-00003.npy b/full_data/c4/part-14-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..c0f85494de9292fd97713ffe60fcf05047087e6e
--- /dev/null
+++ b/full_data/c4/part-14-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7464da295ad0c260341f14d73e70bb2526344ad26fa380c0a50b0c344a6f50a
+size 1762368000
diff --git a/full_data/c4/part-15-00000.csv.gz b/full_data/c4/part-15-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..ae305f02f71b053233cd09b086cbc9b0d2c1bda1
--- /dev/null
+++ b/full_data/c4/part-15-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a917a767040437cc2803f085fe2cf3828c54775caf54a2b91c59a8c6b5d8c5
+size 68101031
diff --git a/full_data/c4/part-15-00000.npy b/full_data/c4/part-15-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..e1acf9b58d5a8ff480682b2b58b9e2f9d0e9f75c
--- /dev/null
+++ b/full_data/c4/part-15-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432dda1e79b758fd2da6c1abfc906c994f4eb57f1f7e891ff502d10d4099cb3c
+size 2147482874
diff --git a/full_data/c4/part-15-00001.csv.gz b/full_data/c4/part-15-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..932c6ebcdb200aafc8648da84589c0a19b82f3f6
--- /dev/null
+++ b/full_data/c4/part-15-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fbabf2195c29497d104eb6359a283127013a230fa71031131cc2decae581fd7
+size 62017629
diff --git a/full_data/c4/part-15-00001.npy b/full_data/c4/part-15-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8ed06c2ab0cae001e7fc8acb843c9b7af8164567
--- /dev/null
+++ b/full_data/c4/part-15-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a908de3a7878632b9aeee7636ca3a3741c21d7283b6d62463213a2a431162f7
+size 1955208612
diff --git a/full_data/c4/part-16-00000.csv.gz b/full_data/c4/part-16-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..eacaed66d5ce7238907b254e17f265bbd42379d0
--- /dev/null
+++ b/full_data/c4/part-16-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b926d016a94f7ba690479add356e5b4ac16f16b412010a9e2cf5f0c4fccb4253
+size 67977021
diff --git a/full_data/c4/part-16-00000.npy b/full_data/c4/part-16-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..715c3c1da4fa5412ee6ef23a97a9f5e4a17959a2
--- /dev/null
+++ b/full_data/c4/part-16-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceedac5fe7894bd5f75f5bf76b60fea6751474579f700f1501d3e543e704b707
+size 2147477490
diff --git a/full_data/c4/part-16-00001.csv.gz b/full_data/c4/part-16-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..a28d1014bdb097113a78a2467e400ed8a747e157
--- /dev/null
+++ b/full_data/c4/part-16-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a597400cdd7de446a64fdf263de8418cd238bb7f0d7adcaa5f6f8a0634701fa
+size 61856241
diff --git a/full_data/c4/part-16-00001.npy b/full_data/c4/part-16-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f97def039aada1c5d17a1045ef3cd1bf74662b80
--- /dev/null
+++ b/full_data/c4/part-16-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb35fd89f30cdcd19a54004bb9eecf39a03d3da4f55ba19f531ee1b36841237
+size 1953931836
diff --git a/full_data/c4/part-17-00000.csv.gz b/full_data/c4/part-17-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e88caeb4ade59198211a2ff60a978c03ee941386
--- /dev/null
+++ b/full_data/c4/part-17-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9626f9f12325eb23e92dd37f4f367a32b9124aaae1f1030348361f8a873957fc
+size 68387062
diff --git a/full_data/c4/part-17-00000.npy b/full_data/c4/part-17-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..70fe6a37de866738b00a96ac4c2ac36fdee5a223
--- /dev/null
+++ b/full_data/c4/part-17-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49bb8e3dbb7b0485bbc6e666262e52816de9762b61ef276666a628c9d0d9313c
+size 2147483106
diff --git a/full_data/c4/part-17-00001.csv.gz b/full_data/c4/part-17-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..7453b42cf91a02b64b2fea4b9a87f78ca0b4fa6e
--- /dev/null
+++ b/full_data/c4/part-17-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97c191c4c03399dc4bd11881a0d096755ead7615a9a19e2282be19ccf0cec466
+size 68367669
diff --git a/full_data/c4/part-17-00001.npy b/full_data/c4/part-17-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f4b882440263e1f41ea5b25f06581be58b17974a
--- /dev/null
+++ b/full_data/c4/part-17-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e11959794fb3b62a34a6c57fa05e7839753956aa3c847eb4e8746bb23fc1c12a
+size 2147454156
diff --git a/full_data/c4/part-17-00002.csv.gz b/full_data/c4/part-17-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..c7a1ee6eba7074a336df716259ef1a871fc810d9
--- /dev/null
+++ b/full_data/c4/part-17-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb079622a712b94a16a7cd138bf0de709d77a817bc0363bccef9c7498c2bbf9
+size 68511185
diff --git a/full_data/c4/part-17-00002.npy b/full_data/c4/part-17-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f6f43bdb3a6e292bfd3e31c387bff67d8f749e99
--- /dev/null
+++ b/full_data/c4/part-17-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e17773f85ecd931caf69694fd038b1075fc12db6b58a1ad9cbc20c9cc74ce0
+size 2147483634
diff --git a/full_data/c4/part-17-00003.csv.gz b/full_data/c4/part-17-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e961b6ab80712dfbd98ea3cbf11383d6f62d81a3
--- /dev/null
+++ b/full_data/c4/part-17-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74b830027995bd0b03854571f189254a64e2aa01ebbb4843a7cadd3bcd8fca9b
+size 56237469
diff --git a/full_data/c4/part-17-00003.npy b/full_data/c4/part-17-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..1eda216c373e10b7e2b4329980d90a16364c78d5
--- /dev/null
+++ b/full_data/c4/part-17-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4bcb3092d358ce1220587e7395b1392147f6dd2b7ada0510f2762940d432378
+size 1763251842
diff --git a/full_data/c4/part-18-00000.csv.gz b/full_data/c4/part-18-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..6743737c2f894c0cc4668c53a6ac2fccc4be2282
--- /dev/null
+++ b/full_data/c4/part-18-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:325be0124f44c4fc1c80d8df035a72f0bb7d5f7330ab13e3dd2f7c1331af159e
+size 68166499
diff --git a/full_data/c4/part-18-00000.npy b/full_data/c4/part-18-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..b5f991c6d1ae7ae6542ce9f16b3bfeb938dcf56a
--- /dev/null
+++ b/full_data/c4/part-18-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b898c5cbe58dcde956d53e824b954e76d29a3451e558a321746c08f9557c26
+size 2147482770
diff --git a/full_data/c4/part-18-00001.csv.gz b/full_data/c4/part-18-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..94377c72585ba9c876d6662530c8a553f97158e5
--- /dev/null
+++ b/full_data/c4/part-18-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2134429974ff37799faca11cdccdc035d8fa411a019eb2c7a60e16d1e90b06c
+size 61951116
diff --git a/full_data/c4/part-18-00001.npy b/full_data/c4/part-18-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..e446ae78acd3a58e69a168c3fbd2d46c8ed57b4e
--- /dev/null
+++ b/full_data/c4/part-18-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c66f496ecccdd2ff9b1e8d04ee7da3e6d79920f2cb24cb1c3fa7e7d76e4e27d0
+size 1952955544
diff --git a/full_data/c4/part-19-00000.csv.gz b/full_data/c4/part-19-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..2c3805d3b27e1e77eb2ca5e2845f6f27d8d45765
--- /dev/null
+++ b/full_data/c4/part-19-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8331108605f6dd9868c6038bbff1a22f5c7b5a281738faa3b425388b483e5dec
+size 68121044
diff --git a/full_data/c4/part-19-00000.npy b/full_data/c4/part-19-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..c950edc7d21efe4c694a1f3e9c0c2469afbeab7d
--- /dev/null
+++ b/full_data/c4/part-19-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce048dce794e4ae722843f21f137ffb9c6395ab26b02772736811a5a6994724b
+size 2147482656
diff --git a/full_data/c4/part-19-00001.csv.gz b/full_data/c4/part-19-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..5e3dc651c969c4ed71dcff431f4ea2435f7604f3
--- /dev/null
+++ b/full_data/c4/part-19-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95f1db9e29f370e278c14f0f301806915e95fcd2eb04cf7eee231f2aeb8cfb55
+size 62001847
diff --git a/full_data/c4/part-19-00001.npy b/full_data/c4/part-19-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8b1beb760505e3a2c59c95243a6c7e2ac9114371
--- /dev/null
+++ b/full_data/c4/part-19-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda1ddc5003e2c745d49f5b06ae42c58cdac4f4a2c859b7a21aecdf54ba363ca
+size 1963727714
diff --git a/full_data/c4/part-20-00000.csv.gz b/full_data/c4/part-20-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e64d67593747e010088ce5b67539a188219ea735
--- /dev/null
+++ b/full_data/c4/part-20-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8c808221eb7f3774f3ec7c8ce27e7e2d9e5e0e78e6a4041ac706066d96140a
+size 68434255
diff --git a/full_data/c4/part-20-00000.npy b/full_data/c4/part-20-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..bbbdb6e95236c056206d4579229438b025e0e6fa
--- /dev/null
+++ b/full_data/c4/part-20-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e36414fb405529d11a4177b485639f2dea92a589f4d7c4dea412709ec78d052
+size 2147482700
diff --git a/full_data/c4/part-20-00001.csv.gz b/full_data/c4/part-20-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..462890fa9285c4272367d98cbffcc15e15ec358c
--- /dev/null
+++ b/full_data/c4/part-20-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d9f8d2edbcfcdcc117b5dc689d7541a79b4f5b2eb4f5b63488a5ff12061160b
+size 68302617
diff --git a/full_data/c4/part-20-00001.npy b/full_data/c4/part-20-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f3178dea74f4d1c7b231f80d9b03d1c11428170c
--- /dev/null
+++ b/full_data/c4/part-20-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edfa592a027aef4c68cb4102dfeefa2ccd87bf9053a1b4ae74c2be6193b2949b
+size 2147483362
diff --git a/full_data/c4/part-20-00002.csv.gz b/full_data/c4/part-20-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..96a838e66b2a29e8487ff1d60e1e01e53a98b76d
--- /dev/null
+++ b/full_data/c4/part-20-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed97cd69264fc65961a44378eebf723ce2abb6e344a7e6afb8fe16d22e79485
+size 68435625
diff --git a/full_data/c4/part-20-00002.npy b/full_data/c4/part-20-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..c983e0e7d3bd5091c518a18da0b2b3e48f664052
--- /dev/null
+++ b/full_data/c4/part-20-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f39943087e99d0206fb39cdb00368ad58a9641a2b4d14bfb2e5a7785a2178bb
+size 2147483038
diff --git a/full_data/c4/part-20-00003.csv.gz b/full_data/c4/part-20-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..2c64db103cee11deebd1718fe3606ece601a8c8d
--- /dev/null
+++ b/full_data/c4/part-20-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71fa6bbca35031c24aeb23271ba5f59bc861c360e4f37811a8a290e1f5e19f4f
+size 56378067
diff --git a/full_data/c4/part-20-00003.npy b/full_data/c4/part-20-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..6b8dbd5fea49d4257c777c7676c721f676ff45b9
--- /dev/null
+++ b/full_data/c4/part-20-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:601aa8ffc7aa478c98471810fd297b99382e101e136e5bbd8ac7b1a5ec7704dc
+size 1766285590
diff --git a/full_data/c4/part-21-00000.csv.gz b/full_data/c4/part-21-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..77879705068feb44c6b13fede47117752b35d46d
--- /dev/null
+++ b/full_data/c4/part-21-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de0ae834bb5327a6cb356babe1a0c493f1c15544bb7cfeb7003cb5f4c3f5be79
+size 68002705
diff --git a/full_data/c4/part-21-00000.npy b/full_data/c4/part-21-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d56f68f689d2385c9925fc30c5e00f21d1d09d43
--- /dev/null
+++ b/full_data/c4/part-21-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0b288f7258e44596fbbe8e5edd2bef3df37bf3acccbe9b2fc10c784c150fe4
+size 2147476168
diff --git a/full_data/c4/part-21-00001.csv.gz b/full_data/c4/part-21-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..f95681685a3415b17de5756bdf364b76025907cd
--- /dev/null
+++ b/full_data/c4/part-21-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67131e4e01e838afd2c265abf54d2b3aea3e005d733e5b42033b1c35106b5700
+size 62118719
diff --git a/full_data/c4/part-21-00001.npy b/full_data/c4/part-21-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a375e0dfd36fe200bc0f88187b8e500551d4c629
--- /dev/null
+++ b/full_data/c4/part-21-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fca858a6a596d37e959650316f7fd10a28a1697791368672132af7b08c3798d
+size 1958267928
diff --git a/full_data/c4/part-22-00000.csv.gz b/full_data/c4/part-22-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..83ddb735dc431e8aa1c43ca08f62d543f935c7b9
--- /dev/null
+++ b/full_data/c4/part-22-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c2858a1b7f22f6246bb29a500c225bd180bdb36f71d94581589b128b27daf9
+size 67978363
diff --git a/full_data/c4/part-22-00000.npy b/full_data/c4/part-22-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..ef8dc2ca5171411556417378c9e3040ffc602b87
--- /dev/null
+++ b/full_data/c4/part-22-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1449778ac15cd64842f5fcec4ee316d057130be130504e1b7799537156ec6e74
+size 2147479232
diff --git a/full_data/c4/part-22-00001.csv.gz b/full_data/c4/part-22-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e00cf2a6a83d184bf4da9fb63855a4ae7c538be8
--- /dev/null
+++ b/full_data/c4/part-22-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fffe4d05aa5bb9eab3947384402332fdcccd02d254b190b4097018c826c7e7bf
+size 61859832
diff --git a/full_data/c4/part-22-00001.npy b/full_data/c4/part-22-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..4911b91903a889c01474bc66eca0c77be0f662c3
--- /dev/null
+++ b/full_data/c4/part-22-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78215da6400463f8fa775df1c204a8a0a95872755bdb63ae73f794bd63f2c1e1
+size 1953018832
diff --git a/full_data/c4/part-23-00000.csv.gz b/full_data/c4/part-23-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..2a1472d0d766d6e6a73dea48386f3705b9df5ce2
--- /dev/null
+++ b/full_data/c4/part-23-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441528c9d2f11e132f34f19966b648a3dc51289a8f6f35145655ca050b4bf62b
+size 68293606
diff --git a/full_data/c4/part-23-00000.npy b/full_data/c4/part-23-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..ccbfcd2c56e53b5a43ccbae7663cbf75a98b5eb8
--- /dev/null
+++ b/full_data/c4/part-23-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f301ebc7cf479c2d7b019da15de99fdf3c0a4318bdb641dd265bfd6e3529f09
+size 2147482594
diff --git a/full_data/c4/part-23-00001.csv.gz b/full_data/c4/part-23-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..254e60d5b08b90059d4d5fe3f433f0c2397fa4ef
--- /dev/null
+++ b/full_data/c4/part-23-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a19a61132fc037da8d1a953632580b7e31ebd4a39a18874f611c5bb6f5e55681
+size 68436705
diff --git a/full_data/c4/part-23-00001.npy b/full_data/c4/part-23-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..c7001c4f4294a44fb2339eae15cfc51a6f7c86a9
--- /dev/null
+++ b/full_data/c4/part-23-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a824f017dd26ced8b62af10e5f52bc4b8a4ea6f81b0a91ea7eb6418fa430df
+size 2147481766
diff --git a/full_data/c4/part-23-00002.csv.gz b/full_data/c4/part-23-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..c3c9cf33952d9143c969c571260e00bcc6d06e0a
--- /dev/null
+++ b/full_data/c4/part-23-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d41a2a90f9fb9bebc10e9b6398fedda1729e1cce0df4fe8f3a1d00e69d11a9ff
+size 15728591
diff --git a/full_data/c4/part-23-00002.npy b/full_data/c4/part-23-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..4b733b577119ceae87bba940e3dab9b475dbac8f
--- /dev/null
+++ b/full_data/c4/part-23-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8280134d83d79c6383e6a75f38848a7ab89241c2a64de816a7e7e4596dc4219
+size 496477346
diff --git a/full_data/c4/part-24-00000.csv.gz b/full_data/c4/part-24-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..3f43391e6b0ead933ee7c06643d3347e72a218d6
--- /dev/null
+++ b/full_data/c4/part-24-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f28b8430a26886a369d9f83a8dec583806f8032e32a7cb35ceaba9789400d1
+size 67986075
diff --git a/full_data/c4/part-24-00000.npy b/full_data/c4/part-24-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..907722852a5031ac318d4bc04515ad3c0a3989da
--- /dev/null
+++ b/full_data/c4/part-24-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4353b56827375a396c0847c356c0a106e5d9b4e6870487cf373d3a2af6a7cc15
+size 2147483472
diff --git a/full_data/c4/part-24-00001.csv.gz b/full_data/c4/part-24-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..db95da9a75a8ecfc626b5dd2b5adadb5d9fb38c0
--- /dev/null
+++ b/full_data/c4/part-24-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:764b9b3a758728cb130eb3217f87c5cff81a02d800d8a0ed3acfdf514a7a1127
+size 62130509
diff --git a/full_data/c4/part-24-00001.npy b/full_data/c4/part-24-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8b2827f4cd52b322733b7cf1076ded0720e1f6f1
--- /dev/null
+++ b/full_data/c4/part-24-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81f9d028f0ff974cbcc36a5630d12fd3f89124506ff7febb61c55aa0e6ba3753
+size 1957515864
diff --git a/full_data/c4/part-25-00000.csv.gz b/full_data/c4/part-25-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..fcc5c4718fea94cacbd3e4e7a50d02b5dcb56625
--- /dev/null
+++ b/full_data/c4/part-25-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0a8b7635a46a889f6fdd89e656bba18dc97eed276da84731bf74aaf0e0da606
+size 67871455
diff --git a/full_data/c4/part-25-00000.npy b/full_data/c4/part-25-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a7e2b07e43963e4064b5cd0f846878371b13bbc5
--- /dev/null
+++ b/full_data/c4/part-25-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a14906605d61af5d310029790f044e7c4a6232f3a52c54faec34e0068450b967
+size 2147483362
diff --git a/full_data/c4/part-25-00001.csv.gz b/full_data/c4/part-25-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..3c2ecaac8f8ae7b026c754a9d753e6aa6d686b10
--- /dev/null
+++ b/full_data/c4/part-25-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e34499a28288f95527bb7e1fee19e0a3b61c5ccda367f8f946950f084194c7ee
+size 61964268
diff --git a/full_data/c4/part-25-00001.npy b/full_data/c4/part-25-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d0e01b6b5b26e30e0844013a0b217809fb7f3b24
--- /dev/null
+++ b/full_data/c4/part-25-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e5afbc6b9f56dd38d0287f5037f6744146ef40782e7a5fa3ed9ae4689cf196f
+size 1961448802
diff --git a/full_data/c4/part-26-00000.csv.gz b/full_data/c4/part-26-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..4cec45138d9c28783a5bb98d7bac4b782d1acd5a
--- /dev/null
+++ b/full_data/c4/part-26-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a3cef86e718510de2974ad397683011c80c95b5c3c61261500c58bceee83c48
+size 68320576
diff --git a/full_data/c4/part-26-00000.npy b/full_data/c4/part-26-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8ff374001bf623b10357bf293a9217346db38121
--- /dev/null
+++ b/full_data/c4/part-26-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2672629cff854f4ff69cdbf33ee5093df4732948515d4dcec287959152443bcc
+size 2147482996
diff --git a/full_data/c4/part-26-00001.csv.gz b/full_data/c4/part-26-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..19a2a77b26965394b9d292980972073d7ac459cd
--- /dev/null
+++ b/full_data/c4/part-26-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67029c616ecce5e0855a8f0c8d422db988a0db11635b5077219e4aa7afe91337
+size 68435392
diff --git a/full_data/c4/part-26-00001.npy b/full_data/c4/part-26-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..74d384d4b4ee5b8642cdd30dd1c7e817e6cfba07
--- /dev/null
+++ b/full_data/c4/part-26-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd1707cfde3b29206af7a2274a99623cc6786f1483cea95db29fdafa0419cfaa
+size 2147481374
diff --git a/full_data/c4/part-26-00002.csv.gz b/full_data/c4/part-26-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..fa17f3e350c1abbcb9f630f5db1b748b157caba8
--- /dev/null
+++ b/full_data/c4/part-26-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74b6ee5d9cd4fd17a504bbadd364be848a15b7d919cd395e7eca454f1345ffa5
+size 68463057
diff --git a/full_data/c4/part-26-00002.npy b/full_data/c4/part-26-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d99e42aad3d23ae2336c668b76cdda1f4d47baf0
--- /dev/null
+++ b/full_data/c4/part-26-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:464a59bf90f0e410f27bd232409b87aef12a4f226ec5101fba446c2783b8c378
+size 2147477646
diff --git a/full_data/c4/part-26-00003.csv.gz b/full_data/c4/part-26-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..5733fe3ea8a6dc7002ae6055360ada174ff9c2e2
--- /dev/null
+++ b/full_data/c4/part-26-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f8447bf282e89d9d68a1215a260be193b53ca5083ed5144b00e1994bd199726
+size 56331395
diff --git a/full_data/c4/part-26-00003.npy b/full_data/c4/part-26-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..ae4f1cc6e73d469c7b7ce621637a119d892aa658
--- /dev/null
+++ b/full_data/c4/part-26-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4210f55c2530c08ef8c64c422473321da9ae2041e7c587dd9f89568a10aa4ad0
+size 1766073128
diff --git a/full_data/c4/part-27-00000.csv.gz b/full_data/c4/part-27-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..7b228340c7afc8f046615b99fec2c78b30279a0f
--- /dev/null
+++ b/full_data/c4/part-27-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1723654c248e602d5659c16dc2fafc7acc709884d6fa93da856a7240844f5fdb
+size 68097794
diff --git a/full_data/c4/part-27-00000.npy b/full_data/c4/part-27-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..6ae5dd6a8c253c416f7b8699d286939fe0eab756
--- /dev/null
+++ b/full_data/c4/part-27-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b389e9fa4ad9f36e365f65790e8ed3346bb3f1d139fb9db3174b725a631ac66
+size 2147482828
diff --git a/full_data/c4/part-27-00001.csv.gz b/full_data/c4/part-27-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..8282d0cc45bb34f830a9111cbd348b1eb8428590
--- /dev/null
+++ b/full_data/c4/part-27-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1b66b7a486d51c3c5f248fe46f94c56e87e3489b1e9d2cdacc843bfc790506
+size 62020463
diff --git a/full_data/c4/part-27-00001.npy b/full_data/c4/part-27-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..c954412756adf700f43b8ecf2198686e32462e95
--- /dev/null
+++ b/full_data/c4/part-27-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da5ea7dcf6bbdd837ad789aeb01b5d59701c892055e2ff894857f2e87726b5f9
+size 1955562254
diff --git a/full_data/c4/part-28-00000.csv.gz b/full_data/c4/part-28-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..0cd9b5c86937099175aae7d40a0a34fa1c1fbb23
--- /dev/null
+++ b/full_data/c4/part-28-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5daad6df159c3e129490d507740c33d8d5cdd5baaf06147b74e24dee6c1aeb5a
+size 68027910
diff --git a/full_data/c4/part-28-00000.npy b/full_data/c4/part-28-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3cdf769c10759c295b2594a74308dbd61fbfd6b1
--- /dev/null
+++ b/full_data/c4/part-28-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f032d3c519607d1db13d23ec14d605833e3389a6fea507888e13dc692a8fd6
+size 2147482436
diff --git a/full_data/c4/part-28-00001.csv.gz b/full_data/c4/part-28-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..f304563e5323a4f96452fd29c10f1b3c43e472ac
--- /dev/null
+++ b/full_data/c4/part-28-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da4d8a826e57522f055a51e8098c0cc03322446fe73a730083878e3d41426cc
+size 62093458
diff --git a/full_data/c4/part-28-00001.npy b/full_data/c4/part-28-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..fb334ae9ca2b4fe1e9562911dd107a191698784c
--- /dev/null
+++ b/full_data/c4/part-28-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e983c86e8629649ae49b1855ade2daeac347850b13cada2ee185820f3d955d6a
+size 1963580496
diff --git a/full_data/c4/part-29-00000.csv.gz b/full_data/c4/part-29-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..d820ff938deb11e93b8902fcb0a02af2de07c456
--- /dev/null
+++ b/full_data/c4/part-29-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df7aad36824de6bd6b3fbdc5b0743d99b1b4d398e91a7a0548cf96b496e7752b
+size 68527706
diff --git a/full_data/c4/part-29-00000.npy b/full_data/c4/part-29-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..cdad253ee9e028c4a099aade5474ebb17e7ef8a1
--- /dev/null
+++ b/full_data/c4/part-29-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b038012e6c858ae2c53ec70bb801897663af40c347c774ed08378d3c25b2ef8
+size 2147481496
diff --git a/full_data/c4/part-29-00001.csv.gz b/full_data/c4/part-29-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..ea9e26739bfd4aaee74f8bb2944d13070654a7d4
--- /dev/null
+++ b/full_data/c4/part-29-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9668e5fb98e73cc6badf0aab0856efa85f59b5ae5fc6508e1030a465651e9d20
+size 68505325
diff --git a/full_data/c4/part-29-00001.npy b/full_data/c4/part-29-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..61216e8e5c51affd94b20b3d13f4f99fd9c09db8
--- /dev/null
+++ b/full_data/c4/part-29-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f886ce5764d3fdd4e5f2ec52aaeb23fd1a45820aa7186b9e71f7b2f66792987
+size 2147480710
diff --git a/full_data/c4/part-29-00002.csv.gz b/full_data/c4/part-29-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..625cddd985dfd591fc0289c6842b7a6bb53fcbb1
--- /dev/null
+++ b/full_data/c4/part-29-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d82dad20ee1cf40a908cd73b0e4b01d2b7176a9d3d9ac9d83995c03207fa9d
+size 68470523
diff --git a/full_data/c4/part-29-00002.npy b/full_data/c4/part-29-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..b499cc41faf3e0cd94ae0e72128dfa9fca4c53ef
--- /dev/null
+++ b/full_data/c4/part-29-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba7d6494c14c4f57c03af4ce8d390d7833fc7ce2e91a5be5ce3993c11106287
+size 2147483514
diff --git a/full_data/c4/part-29-00003.csv.gz b/full_data/c4/part-29-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..29add6b9bdec101d198e69bd143f97b15d337012
--- /dev/null
+++ b/full_data/c4/part-29-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a18430574cc10599804f66cbe9237fe745ffc5e0b94c41058e89ca59905471
+size 56052714
diff --git a/full_data/c4/part-29-00003.npy b/full_data/c4/part-29-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..75552cb1b9ad946cbe44b253f32840bffb291425
--- /dev/null
+++ b/full_data/c4/part-29-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ebdd9c52385b8866dcbb3f1e635755da3c100cb61ecff420389a69bd5474ade
+size 1760874434
diff --git a/full_data/c4/part-30-00000.csv.gz b/full_data/c4/part-30-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..5731f725cdde16e3e6a55a522cc38aa1ea89bf72
--- /dev/null
+++ b/full_data/c4/part-30-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a919dbc94a819dd083536d27dc04ae79c1c91108d251dee495494d6b5f99525d
+size 68127902
diff --git a/full_data/c4/part-30-00000.npy b/full_data/c4/part-30-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..b84bf0e254f9f005c5b6c3b2de4c87e9310aef56
--- /dev/null
+++ b/full_data/c4/part-30-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c512b75d3129882e026b705b9474db8f7b4fbf6191354b80017b79361fb82d2c
+size 2147470812
diff --git a/full_data/c4/part-30-00001.csv.gz b/full_data/c4/part-30-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..4b1b2436d0b10f2d815a123455919e448ebd9576
--- /dev/null
+++ b/full_data/c4/part-30-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db63ad43d8f5f4a9331a6e3c87be07b4da01e2cfcfaf94ec0e9d821b4dfb518
+size 61993389
diff --git a/full_data/c4/part-30-00001.npy b/full_data/c4/part-30-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a1abe89b584f7b23da8f19c4e615511b44d41c20
--- /dev/null
+++ b/full_data/c4/part-30-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bb2f84937365c6c8494484dd2fdbb1a8601f4ad731a2011272ef1405475594c
+size 1954560618
diff --git a/full_data/c4/part-31-00000.csv.gz b/full_data/c4/part-31-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..aaf1b4ceaa521cb8a3d3bf783e3407e5572c918a
--- /dev/null
+++ b/full_data/c4/part-31-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a0991b66d36d05cc7c484727491c93bbb218f6d9874eeca2a9da23833ff2ec
+size 68413599
diff --git a/full_data/c4/part-31-00000.npy b/full_data/c4/part-31-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d4e3b5d12d5049afb0cbd5b7ba6567b719385a59
--- /dev/null
+++ b/full_data/c4/part-31-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f45f242d71c0ad866c2fea45a5941b9b189081f8a0950a5ecedbed6d4b07bec7
+size 2147475058
diff --git a/full_data/c4/part-31-00001.csv.gz b/full_data/c4/part-31-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..47663d1a42af5e10dafda34e7e7f497cb41238a2
--- /dev/null
+++ b/full_data/c4/part-31-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246e03e9685461e99429b470d43559b67a46866aaa207af0f54a125025cb8fb4
+size 68447463
diff --git a/full_data/c4/part-31-00001.npy b/full_data/c4/part-31-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..9c44cbfae726d8ca029da3d39023b2372a015afc
--- /dev/null
+++ b/full_data/c4/part-31-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce3ee86ceb7ac531b3a94e489ef99003b0e011f39a782c208bd39f16324adfa
+size 2147483562
diff --git a/full_data/c4/part-31-00002.csv.gz b/full_data/c4/part-31-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..f452dcab7ebb24c287d2c3cc48511ff8df749f2f
--- /dev/null
+++ b/full_data/c4/part-31-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b87bfd6c6ae91700f637accb5cacc6e4e7136a3a90ddaee560f2d89d4fbfdf7
+size 68431746
diff --git a/full_data/c4/part-31-00002.npy b/full_data/c4/part-31-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..61eac438b991fa37ed378f12af2891a74dbe1bdd
--- /dev/null
+++ b/full_data/c4/part-31-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1649e6520d2f89eb139185f65ac3ceccf84651218a1ddaad968dae743d55fd2e
+size 2147482668
diff --git a/full_data/c4/part-31-00003.csv.gz b/full_data/c4/part-31-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..06a0b54d0e0d419695065d81774785b9b5833ada
--- /dev/null
+++ b/full_data/c4/part-31-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f20bb3c8a30cf0c2d7d38dffa355a8ec192ddf64db64e9fcb1915b4eee29c1
+size 56288869
diff --git a/full_data/c4/part-31-00003.npy b/full_data/c4/part-31-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a5f56a862ac7bf55bbf740029bdb64701e074c1a
--- /dev/null
+++ b/full_data/c4/part-31-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d194bff49bc676391af0918cb82e774f61f00b627fe135170c93b35d187bdee4
+size 1766867000
diff --git a/full_data/c4/part-32-00000.csv.gz b/full_data/c4/part-32-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..1151fcfe30e16a8bc265e85d7d37b1a3a70df2a7
--- /dev/null
+++ b/full_data/c4/part-32-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede69b1e6b10612d1d7254925ec182d855642f30090a281aae22b61a20149f03
+size 68066202
diff --git a/full_data/c4/part-32-00000.npy b/full_data/c4/part-32-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..c060e28f82716d0a9a12e413b1ff8a95e2928c2a
--- /dev/null
+++ b/full_data/c4/part-32-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a6fa066605ee93a89fbbf60935c6b1d2d74c3ab96e3cce473205af079006bc8
+size 2147482868
diff --git a/full_data/c4/part-32-00001.csv.gz b/full_data/c4/part-32-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..45d98e6b31f9ee2f9606e941736a4b8bb05dee0e
--- /dev/null
+++ b/full_data/c4/part-32-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae078ed24ffcf72168ff6b867396ba2e162859984051c914b2e069e2487818c5
+size 62054971
diff --git a/full_data/c4/part-32-00001.npy b/full_data/c4/part-32-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8a6f0b3cb6ffacd2fe872357d67d6179bbbdb527
--- /dev/null
+++ b/full_data/c4/part-32-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47460776d0c4ab40bc4ba78ab8eece669a973dba09407a192abcc93f5886d5f5
+size 1955543864
diff --git a/full_data/c4/part-33-00000.csv.gz b/full_data/c4/part-33-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..7fb21d4287fa7fdebdb622e70faf21dff9b62602
--- /dev/null
+++ b/full_data/c4/part-33-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac9383cde13caee09fc2207c0bcb844223081875a665a83bca62ac1e5588e0b
+size 68024011
diff --git a/full_data/c4/part-33-00000.npy b/full_data/c4/part-33-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..83594cf865540ce375dfed965541089e35626cc4
--- /dev/null
+++ b/full_data/c4/part-33-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac126414717722de78f0408d41408b9ceaf69b7b87d94f088e6ccb81e6ab867
+size 2147483644
diff --git a/full_data/c4/part-33-00001.csv.gz b/full_data/c4/part-33-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..1066a3cd2790bc6d8a9cc9be6e5297479cce2ff1
--- /dev/null
+++ b/full_data/c4/part-33-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:419c69e3deaa2b9c49b2a40a98dfa7e545b0d5703b9c9ced29347b687950d398
+size 62098531
diff --git a/full_data/c4/part-33-00001.npy b/full_data/c4/part-33-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..e8e9a0caf393e0e362c9daaaef6ddb891ce216ab
--- /dev/null
+++ b/full_data/c4/part-33-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d349e817c106b39a6b1e3891bf4a45c6c8b5f3436ee134148dcc877f63d8bf
+size 1963699820
diff --git a/full_data/c4/part-34-00000.csv.gz b/full_data/c4/part-34-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..8c561df8657b6a888f52779f17b87b93b382aa14
--- /dev/null
+++ b/full_data/c4/part-34-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b099398a29ebed8df9c9442c452217adbf7fd7b07a2f7a267d88b82ab61623bd
+size 68405476
diff --git a/full_data/c4/part-34-00000.npy b/full_data/c4/part-34-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..0981c3ddfa10320e90d7f7e529291374b70169f1
--- /dev/null
+++ b/full_data/c4/part-34-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd4049771c15eb56867e2d733dec42d2121e5430aeb8bb6f1b35a5a2e5e65b6
+size 2147483570
diff --git a/full_data/c4/part-34-00001.csv.gz b/full_data/c4/part-34-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..61114606a5b86f24d2efe668bce760965fa40a76
--- /dev/null
+++ b/full_data/c4/part-34-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:458021bc95c736bf57b8b57186315203197ba7f11d9a8a9c63da6aaf7aea62a2
+size 68466372
diff --git a/full_data/c4/part-34-00001.npy b/full_data/c4/part-34-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..fa9ffaa23c1bb8990c914622e840b8009a5f1ca5
--- /dev/null
+++ b/full_data/c4/part-34-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77675ccd2a233cacee36796b62afb0c84f0d1908746fe432d674b429b5ce5f82
+size 2147483328
diff --git a/full_data/c4/part-34-00002.csv.gz b/full_data/c4/part-34-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..794b0f9516bd720df79bbb6d82090e95ee72f427
--- /dev/null
+++ b/full_data/c4/part-34-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aaa2d68ece740dfd5adbabf63ff947ca626e6726b8cfedbd4d9cb55abe6fc7f
+size 68401138
diff --git a/full_data/c4/part-34-00002.npy b/full_data/c4/part-34-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3d39c26615a467ab66ade2a6d5c4103e670a855e
--- /dev/null
+++ b/full_data/c4/part-34-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:186b0b4b33b741dddee0ecc636d03b359eea988e89d356bf6244245565877324
+size 2147483276
diff --git a/full_data/c4/part-34-00003.csv.gz b/full_data/c4/part-34-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..5b68589dcfcd433166cbe5e34392e8b5bf65165a
--- /dev/null
+++ b/full_data/c4/part-34-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:916bd970cd4fe289c47451875b499954482055609c97f9c5e3c2f78e33431903
+size 56222220
diff --git a/full_data/c4/part-34-00003.npy b/full_data/c4/part-34-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..025a20a39924bad1af5312031669ce9e8626cdb2
--- /dev/null
+++ b/full_data/c4/part-34-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:354589261fa7ec4ddd595c6ea1b4d975041e86143df8bbaf5ac9495c2cbdc7f4
+size 1761848838
diff --git a/full_data/c4/part-35-00000.csv.gz b/full_data/c4/part-35-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..8a3b24b254df56f52b3431b374d30094c36dda9c
--- /dev/null
+++ b/full_data/c4/part-35-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:675a4d509cffa2c1eee77be8ecd15443d6b609031d53b49232e8ab5139688818
+size 68161847
diff --git a/full_data/c4/part-35-00000.npy b/full_data/c4/part-35-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..30f86414bdfb0f45f946c393cb15b21f6259efd5
--- /dev/null
+++ b/full_data/c4/part-35-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daf875a9751f14d79c1a356e6d967d77f2a07e7f0a30125c616b049f38b977c5
+size 2147479066
diff --git a/full_data/c4/part-35-00001.csv.gz b/full_data/c4/part-35-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..5106a56bab9b4676a69fcf480b9608f40e37f9ab
--- /dev/null
+++ b/full_data/c4/part-35-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e34faf3216382f5f65d250bea19ed6da71270c984b1ad8f4520887d4ac63c47
+size 61955143
diff --git a/full_data/c4/part-35-00001.npy b/full_data/c4/part-35-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f569181fac07e54bf67f55322772921cfe07b264
--- /dev/null
+++ b/full_data/c4/part-35-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4c09ef23ea2864d94bc3d05626dad1abf802cb18d287a572ea791b68cadd4d
+size 1955764682
diff --git a/full_data/c4/part-36-00000.csv.gz b/full_data/c4/part-36-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..d0af58937324a8715fa339fb19a2495075f75aba
--- /dev/null
+++ b/full_data/c4/part-36-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf669a3b3510b2df4d0777074803960b952482db4f723601af42246ffef259e
+size 68134154
diff --git a/full_data/c4/part-36-00000.npy b/full_data/c4/part-36-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..1f8f7fa5fd4b37b8d4a531928da60ce12aac9264
--- /dev/null
+++ b/full_data/c4/part-36-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998bf5b831659b3197e620b737ce04b396f42b8134c750eda4b5402df16fb708
+size 2147482962
diff --git a/full_data/c4/part-36-00001.csv.gz b/full_data/c4/part-36-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..1b4b97c838af84671d6a68753eeb773b43243986
--- /dev/null
+++ b/full_data/c4/part-36-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:641c03d1c9a2a6ccf64be072bc152fa7344599fbef8b6520cea7228b573759fb
+size 61984201
diff --git a/full_data/c4/part-36-00001.npy b/full_data/c4/part-36-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..5f98c9e4059a84e17c7e780fe1d4c5eb82e34959
--- /dev/null
+++ b/full_data/c4/part-36-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:757fdc67d753774bb1071be206abe06ff2e6407850806eff2b93924dea7a4439
+size 1955557708
diff --git a/full_data/c4/part-37-00000.csv.gz b/full_data/c4/part-37-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..fe8a7a137043e21762988f9944755a17239bcb8d
--- /dev/null
+++ b/full_data/c4/part-37-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:224d684e077b3d9baab218b2ef2cdcaea3de9b57e2b659b0ff41ab42b36cd0cd
+size 68373711
diff --git a/full_data/c4/part-37-00000.npy b/full_data/c4/part-37-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..28fb9bc1eecbc57a3a8ff7672451aa3da8d93f68
--- /dev/null
+++ b/full_data/c4/part-37-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e60c01e5564e11081d2acb1f1ebfd9db305fe51c54a7f7d34fbc90a770b9f15
+size 2147483564
diff --git a/full_data/c4/part-37-00001.csv.gz b/full_data/c4/part-37-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..c4b32e9b4b23f4cf338d9c57c117d5b11b4e75f1
--- /dev/null
+++ b/full_data/c4/part-37-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3a2b6987ab5124506f697b963b94b07ea28e0be1a55e682a6a9ce96b934be0
+size 68503689
diff --git a/full_data/c4/part-37-00001.npy b/full_data/c4/part-37-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..84d9ca172be67db304039b475764bf7e8b53809b
--- /dev/null
+++ b/full_data/c4/part-37-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0e70fdb1f7f17365a01fafd981d9ab0c13969e58817df6b7c37ca31a6e6164
+size 2147482458
diff --git a/full_data/c4/part-37-00002.csv.gz b/full_data/c4/part-37-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..06498290213c0371d2d233353e5da8b35dae268a
--- /dev/null
+++ b/full_data/c4/part-37-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95ea0f8ad818f87674407fd3aae8f5fffc0478b26abe04b50e844083d6fd02f2
+size 68540367
diff --git a/full_data/c4/part-37-00002.npy b/full_data/c4/part-37-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..4f438c8612e8d72352a18af4371b85e6f02e83cb
--- /dev/null
+++ b/full_data/c4/part-37-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97b1d6337f36f3a97ad292f5d185a41bf87dcae50d42b673db0cfc22310e38dc
+size 2147483410
diff --git a/full_data/c4/part-37-00003.csv.gz b/full_data/c4/part-37-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..8042e032c3873fda93e401e4aed5b9bf320f1d6d
--- /dev/null
+++ b/full_data/c4/part-37-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d2786776557b1f45fcab3adae3473fb20aae82fe5634e9d19939a31031934a8
+size 56137296
diff --git a/full_data/c4/part-37-00003.npy b/full_data/c4/part-37-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..810de61a7dbf2dd9135a528e3940bd11416a3226
--- /dev/null
+++ b/full_data/c4/part-37-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c666bdfa3b5f57a2007bc8e3accaa5373c04f181ef67c36bf5253395abe55b0
+size 1763648564
diff --git a/full_data/c4/part-38-00000.csv.gz b/full_data/c4/part-38-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..ccb27ca8d11ccc3a81c3a7df051af605f1b156cb
--- /dev/null
+++ b/full_data/c4/part-38-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dea83fd5a4f26b0d63f97df16f42357e699953d81f1961690f0629b535dc176
+size 67973465
diff --git a/full_data/c4/part-38-00000.npy b/full_data/c4/part-38-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8b105c0b1ccfa50cf63b13b51ac1e9740d06e5d1
--- /dev/null
+++ b/full_data/c4/part-38-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041f6ceb58d6045eff833842e107ca8279ba35f52dfe4e4e7229537c0309137b
+size 2147482500
diff --git a/full_data/c4/part-38-00001.csv.gz b/full_data/c4/part-38-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..5efce0849e6bebdded6f13e6dda685252695757f
--- /dev/null
+++ b/full_data/c4/part-38-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e14c8d224b7d93a9ccc5c5f78b79535092b75d74bfafec5eee2b7351f65ed14
+size 62147880
diff --git a/full_data/c4/part-38-00001.npy b/full_data/c4/part-38-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..325c288c2f9243f241a34480c4888dbd4d40d119
--- /dev/null
+++ b/full_data/c4/part-38-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b75ec871effd6cc587dae0e969a309b669912e5117fb78d5ecd3f1ab6b6e73c
+size 1965667006
diff --git a/full_data/c4/part-39-00000.csv.gz b/full_data/c4/part-39-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..447964fc32bce9c412ed393eebbdcacdc1ca8cf6
--- /dev/null
+++ b/full_data/c4/part-39-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a433c08154134904e5eb1890551ba63cc33e220365cebdfc02ccbb697f9507
+size 68062235
diff --git a/full_data/c4/part-39-00000.npy b/full_data/c4/part-39-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3f25967da3dc73f2f88c92ad8e13b9c70dfe059b
--- /dev/null
+++ b/full_data/c4/part-39-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b958c9af93ca19fd012733c0e3ba05f20248b3f486d5314abb56df13b7c530
+size 2147483384
diff --git a/full_data/c4/part-39-00001.csv.gz b/full_data/c4/part-39-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..fc3503f66cfd0e56a03bc6f0a5e0d0ceaf71891c
--- /dev/null
+++ b/full_data/c4/part-39-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b19f12384486c7178414ffe312f8707b644414c83857781ad412947926e56dd8
+size 62056782
diff --git a/full_data/c4/part-39-00001.npy b/full_data/c4/part-39-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..bc3eb22f20c0b08cb83245a2777c48fcc15c0c5e
--- /dev/null
+++ b/full_data/c4/part-39-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2587a708341781723c90070277801af95a49c9ad49a2b7a661d9b2339b4ef86
+size 1958645214
diff --git a/full_data/c4/part-40-00000.csv.gz b/full_data/c4/part-40-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..964f6d94ee85df7704a49fac9e27086c66cd40b3
--- /dev/null
+++ b/full_data/c4/part-40-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ba5de79054ce3df51577f7ee6f40b8eb2cc524dd77475c96c7bfad1d1908f9
+size 68142013
diff --git a/full_data/c4/part-40-00000.npy b/full_data/c4/part-40-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..514c150099a567600982f2bd2f7fb9ed956eec42
--- /dev/null
+++ b/full_data/c4/part-40-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53946107584d4a25678c2721f0815998ef87ede610da0e44e265d96c927670e
+size 2147481834
diff --git a/full_data/c4/part-40-00001.csv.gz b/full_data/c4/part-40-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..f8bb559215478cb0fd23df87c7d2005bc157650c
--- /dev/null
+++ b/full_data/c4/part-40-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a10b76c107f869901c694c8ed7c0da6f7ad013bda3821e0378a29c44c00ce0f9
+size 68324812
diff --git a/full_data/c4/part-40-00001.npy b/full_data/c4/part-40-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8df01f40a7c17cf7606b28f3e46331dcc5b79378
--- /dev/null
+++ b/full_data/c4/part-40-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9abece08df4fcbbe60467fb91a66e903767f45c6584aefbecbdea73b3845c89
+size 2147483016
diff --git a/full_data/c4/part-40-00002.csv.gz b/full_data/c4/part-40-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..2735dae73871835d15f94a47c11a80219fac077f
--- /dev/null
+++ b/full_data/c4/part-40-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20332feccb1659ae57efbd499deb4b7abafbe7a2c997471f32f603d00bed770d
+size 68154854
diff --git a/full_data/c4/part-40-00002.npy b/full_data/c4/part-40-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..00424117147a878a3eb4a3dd4cf872ffeb8e8852
--- /dev/null
+++ b/full_data/c4/part-40-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acee3893f4777c044cfc1178d0420e54f7feee0f41985b818a0f0564ed122f3e
+size 2147476060
diff --git a/full_data/c4/part-40-00003.csv.gz b/full_data/c4/part-40-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..f65271cb93c7fcabac29160053208b2ff0e70497
--- /dev/null
+++ b/full_data/c4/part-40-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83cca7441d9c16e80c0c35ae42ce1b75cbc367f431b72a96463ecc1103907263
+size 55734865
diff --git a/full_data/c4/part-40-00003.npy b/full_data/c4/part-40-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..03ec361f93f55c1cbb9c5abbb1aa2bcdc9f7f2d5
--- /dev/null
+++ b/full_data/c4/part-40-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b883a16bf32643e96d670fb93aba91dcf8d331e44c57abf87f868b2ce02500a
+size 1754031242
diff --git a/full_data/c4/part-41-00000.csv.gz b/full_data/c4/part-41-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..c4784f3c43551bb53ddb1b0e8bb0e491135dbc15
--- /dev/null
+++ b/full_data/c4/part-41-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab903c701db63003b3fb8ae35793fd0ad0588b08088af7e4b1aa399cdfd5f12
+size 68095980
diff --git a/full_data/c4/part-41-00000.npy b/full_data/c4/part-41-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..926b9f7b5192145a30724c5b6b473fc2ee74318a
--- /dev/null
+++ b/full_data/c4/part-41-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c9d87de7d91d7104dd2c68b0ff8a4218db440809917d8600bafcd5a2e56c932
+size 2147481844
diff --git a/full_data/c4/part-41-00001.csv.gz b/full_data/c4/part-41-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..8c76d4208851a569489048acdeb234acc4742f6e
--- /dev/null
+++ b/full_data/c4/part-41-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:038e0d255c6e36816d57b4d015277012734403513b180498fa43b0552948a5ab
+size 62023735
diff --git a/full_data/c4/part-41-00001.npy b/full_data/c4/part-41-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..375bb23359fc7a1cdd0101e26b121ea57c5d6b89
--- /dev/null
+++ b/full_data/c4/part-41-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf1ac7c5fb91e6a7c5353f35309ccce8458be2deb98b809f223723b34d569f1
+size 1958607294
diff --git a/full_data/c4/part-42-00000.csv.gz b/full_data/c4/part-42-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..400367af7e99e5a0541de22e927e4ed821ae86e8
--- /dev/null
+++ b/full_data/c4/part-42-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836faf767a23e4b3f8d4a661db2abe95e61c337ab89426a48f9b4cdc83f5f4ef
+size 68219343
diff --git a/full_data/c4/part-42-00000.npy b/full_data/c4/part-42-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..4f28043b1dd8a67bc22de06989099c5867288390
--- /dev/null
+++ b/full_data/c4/part-42-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e28e6809eac6cdd9984f890206a0afcdf86427bce15ceb5275a6e998e6d605
+size 2147483552
diff --git a/full_data/c4/part-42-00001.csv.gz b/full_data/c4/part-42-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..4e289a96a82afdf4896229b87248e71761dbe9ce
--- /dev/null
+++ b/full_data/c4/part-42-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0836e8caea12de158274a366ca51f31a3fb5aee2b3fc993a1563be8cddf4fd3
+size 61898743
diff --git a/full_data/c4/part-42-00001.npy b/full_data/c4/part-42-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f1d3331e526c8b51710549d942dccb35ddd9c59b
--- /dev/null
+++ b/full_data/c4/part-42-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc32051a90f2ffc1bded4291a33b9b74f730d6db27d2891ec94575a1adb6a474
+size 1949949088
diff --git a/full_data/c4/part-43-00000.csv.gz b/full_data/c4/part-43-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..848268bb5302a1a83dbdc426c1de260a1d35e4cf
--- /dev/null
+++ b/full_data/c4/part-43-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c704c92ef138b8f87ab18a77bdcf73e7db1174b2af38919f5dd44730eb0ce59c
+size 68117035
diff --git a/full_data/c4/part-43-00000.npy b/full_data/c4/part-43-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..b11dbda955f1fefd188b31e15221f20376985ef7
--- /dev/null
+++ b/full_data/c4/part-43-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30588820d2ce3ab0175e8dc67069e9305a4fcd10a8ed7a23a004d75140d8c3be
+size 2147483630
diff --git a/full_data/c4/part-43-00001.csv.gz b/full_data/c4/part-43-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..53209afe5fd8b344e51fff00eb438a9382784f2d
--- /dev/null
+++ b/full_data/c4/part-43-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f243f01baca7f6b1a886be69dad076f13b35afdb129a68bc8582af30fd656d9a
+size 68270226
diff --git a/full_data/c4/part-43-00001.npy b/full_data/c4/part-43-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..101839e6862ee48e4d0964471bc943bb30ee96b9
--- /dev/null
+++ b/full_data/c4/part-43-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aee568d3b73a0d3c7c0b42d6873c0d6e349e5d360b44033272fc8598ac47790
+size 2147483646
diff --git a/full_data/c4/part-43-00002.csv.gz b/full_data/c4/part-43-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..1a6232eacdec14696b0e068437c2c64909093ca5
--- /dev/null
+++ b/full_data/c4/part-43-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6af14ef42c27c03460f49a64b2328cbd97a600744c38e76e7ff84bf4ca52892
+size 68064385
diff --git a/full_data/c4/part-43-00002.npy b/full_data/c4/part-43-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..1f00aab97866a9ca83a9fa7ffa6ab3617121dcfc
--- /dev/null
+++ b/full_data/c4/part-43-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eff17fb91dc3a55a70e9bef7dde66e5819e2997ec8c6d889887179ae8a2cbba
+size 2147482778
diff --git a/full_data/c4/part-43-00003.csv.gz b/full_data/c4/part-43-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..de5be12151a294cc52ed71b1730c21a72c6b234b
--- /dev/null
+++ b/full_data/c4/part-43-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5c9d11474ecb874a87e8a2ef552c2cfe1952f7d20b035075c2c73376be21599
+size 55915641
diff --git a/full_data/c4/part-43-00003.npy b/full_data/c4/part-43-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d1ed04e9bb876c534f21b7e1b5cb686eb2150e7f
--- /dev/null
+++ b/full_data/c4/part-43-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:118605f5ee4928b8d0adac8d35bd2cc0e3f42b32865720c469b12563f1758160
+size 1759819794
diff --git a/full_data/c4/part-44-00000.csv.gz b/full_data/c4/part-44-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..568e05e4bfcfdd17805c5f7667cfa644b2493c89
--- /dev/null
+++ b/full_data/c4/part-44-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7728d2be76d9dfaf96e8daf029217c65db387903751fb5aaac83bb6f3e4b4683
+size 68182598
diff --git a/full_data/c4/part-44-00000.npy b/full_data/c4/part-44-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..fc82d074d31a16e68715309450fe03d1879fd184
--- /dev/null
+++ b/full_data/c4/part-44-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:002d0348fad633773bcf2d626722aa428cf5b91ead2504e318f68c1c885af98b
+size 2147480532
diff --git a/full_data/c4/part-44-00001.csv.gz b/full_data/c4/part-44-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..c80b1369b665087b726858e467b44d7582a6dc47
--- /dev/null
+++ b/full_data/c4/part-44-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf888d056d73e88c11c8c7bbacc2a55d2b4397cf29bc16d65769c9e01df11371
+size 61938791
diff --git a/full_data/c4/part-44-00001.npy b/full_data/c4/part-44-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..4185b349d96a82fa08fa7705ab160e6d15459771
--- /dev/null
+++ b/full_data/c4/part-44-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64352a5272e37eec955e7670d880799cba610a7fa2b3732ae1328f3dabeb6923
+size 1952113922
diff --git a/full_data/c4/part-45-00000.csv.gz b/full_data/c4/part-45-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..3fe0b2a53cfe74928bca60a218a62997dd50a4b6
--- /dev/null
+++ b/full_data/c4/part-45-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c40fb75895cacb6eb3c966685430e6b1e320452422317a2656d7d55d86d98e
+size 67901972
diff --git a/full_data/c4/part-45-00000.npy b/full_data/c4/part-45-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..5f4bc3538913783e6058e782b9390440c7ef9ef4
--- /dev/null
+++ b/full_data/c4/part-45-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:415527e448bd5272571c20cf51a968e4aa4482532ba1b54038d0a090d4baf7da
+size 2147482676
diff --git a/full_data/c4/part-45-00001.csv.gz b/full_data/c4/part-45-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..0e7d87f2daea5666547a3b1a0d883732327346ab
--- /dev/null
+++ b/full_data/c4/part-45-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:684448d68eb48f369f8b81d65e5817551892d8a5786528429c9282b6171231f2
+size 61934447
diff --git a/full_data/c4/part-45-00001.npy b/full_data/c4/part-45-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..aaf8df8d56765635c4de7c4383b56d6bd480ccd2
--- /dev/null
+++ b/full_data/c4/part-45-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10a2d6c2410f1fdac382ecf6e80d140f4a2ba8664056070e87313597c19f0b3a
+size 1961358472
diff --git a/full_data/c4/part-46-00000.csv.gz b/full_data/c4/part-46-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..1b416b9aac825d1973fcdd436797cd3d0b40557b
--- /dev/null
+++ b/full_data/c4/part-46-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c516f807f6cc6f2ea70793e9cb9720d294e34bd1273ade8977a9b3e389b395a9
+size 68148329
diff --git a/full_data/c4/part-46-00000.npy b/full_data/c4/part-46-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..341146f77135dc1b4c62d9dc91b872e5d31aa551
--- /dev/null
+++ b/full_data/c4/part-46-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a05d96ac02718c98275741d48056c3bab2153421bce2492371e409abe707cdc
+size 2147482478
diff --git a/full_data/c4/part-46-00001.csv.gz b/full_data/c4/part-46-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..ae26ff26fc1ef9c0b7186d753318e9bb64b2d73d
--- /dev/null
+++ b/full_data/c4/part-46-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a710fdd72ae8059db66d2e245ab7b6b3c6212af64e9957b2644e6cdc7478d6d0
+size 68106707
diff --git a/full_data/c4/part-46-00001.npy b/full_data/c4/part-46-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..819917328175704bdec90bee28f1313fa15540e5
--- /dev/null
+++ b/full_data/c4/part-46-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d04bbcf6ad62ae75b6412ac761577b628dd5a0fd212faec08d83c57f2f55d2a
+size 2147482132
diff --git a/full_data/c4/part-46-00002.csv.gz b/full_data/c4/part-46-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..a915f70b5faa0380f823d81beb924d76f1bee83f
--- /dev/null
+++ b/full_data/c4/part-46-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27d92df27e656a365a860e51469bb203c0864572be80f96b0980e83bbbdd9fad
+size 68331229
diff --git a/full_data/c4/part-46-00002.npy b/full_data/c4/part-46-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..7da9e67f984ce81167ffc3338248db59462512fe
--- /dev/null
+++ b/full_data/c4/part-46-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4328159868d7e654833ece260b01a9ed5b64c0aaec4aef6164d4ddbc161e54fb
+size 2147462618
diff --git a/full_data/c4/part-46-00003.csv.gz b/full_data/c4/part-46-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..ec9b686ee4adea09ef64ade179d3a2231694aae4
--- /dev/null
+++ b/full_data/c4/part-46-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d535bd9a2e1568b26df7e7bca5c4f4e3fc8806bc4c5bc9301356060970d74e6
+size 55771007
diff --git a/full_data/c4/part-46-00003.npy b/full_data/c4/part-46-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a6cf3ec1d2f2050265aad0b70c05e12f5c516b63
--- /dev/null
+++ b/full_data/c4/part-46-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7701b1a5b468632ae3d33d3702423ef3836311d9a69afff8c98671b8627274b
+size 1759395330
diff --git a/full_data/c4/part-47-00000.csv.gz b/full_data/c4/part-47-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..f094cc7bd3db0f1e47d93cb0d6f877049ed13d6f
--- /dev/null
+++ b/full_data/c4/part-47-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ca95a70124c0ea212a7c4fe39f0bd6c1eadecc9088fd71c94bcde866c70e776
+size 67965650
diff --git a/full_data/c4/part-47-00000.npy b/full_data/c4/part-47-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..085a2a8d9d74723f7c6ad2d1f8554a512bd8ca65
--- /dev/null
+++ b/full_data/c4/part-47-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0258e615697e6693f2683cb698938df93f620365e05d13e78191c672e799cd7
+size 2147483564
diff --git a/full_data/c4/part-47-00001.csv.gz b/full_data/c4/part-47-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..6f0aae4814cdc1e3bf7907a804b164b87973b983
--- /dev/null
+++ b/full_data/c4/part-47-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a569fbe4d1c4cce55a8171ac22aa88b883372620c9694703c6549dacaed41f
+size 61871561
diff --git a/full_data/c4/part-47-00001.npy b/full_data/c4/part-47-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3c9dbaac1819164568869ab7f26325674caa621b
--- /dev/null
+++ b/full_data/c4/part-47-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ef0d8d7521298b9ce893fd9618f23fe461a860d636276a49930165ae15ff277
+size 1957124526
diff --git a/full_data/c4/part-48-00000.csv.gz b/full_data/c4/part-48-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..fb3756e53e314c899609047fbd6a0a5106bff092
--- /dev/null
+++ b/full_data/c4/part-48-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71522bca4bf96abaa24f90a834d6e05d35d01a501916cdbf0a837859047cad0
+size 68110033
diff --git a/full_data/c4/part-48-00000.npy b/full_data/c4/part-48-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..d52e7a388ca9ca8488e706317f00cf34631d4ffe
--- /dev/null
+++ b/full_data/c4/part-48-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe29a129b0d84eda02db499ca46f3f371101d3cb4e5aba19568ecdd470679b7
+size 2147480804
diff --git a/full_data/c4/part-48-00001.csv.gz b/full_data/c4/part-48-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..98419fb1afe29850e21def4813fd89b822a06be2
--- /dev/null
+++ b/full_data/c4/part-48-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97c1ec6a48e1237f3308a43758c36a49565a5615f98dec576851a923d4d6cc8e
+size 62009416
diff --git a/full_data/c4/part-48-00001.npy b/full_data/c4/part-48-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..69f206683eb94ac7956de8098b2ba085637e9f00
--- /dev/null
+++ b/full_data/c4/part-48-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c10e6446b96a8a516daf28ae659860a94fc80d6d0eb6274c4c196fb7458ad4a
+size 1958078982
diff --git a/full_data/c4/part-49-00000.csv.gz b/full_data/c4/part-49-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..725c91ae7e43f7dae48d27031d232b6d963e6547
--- /dev/null
+++ b/full_data/c4/part-49-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e4bfd2e5a50713e89ba7028168f03aa9335ffa1878663059163d6e8499c6dd5
+size 68189128
diff --git a/full_data/c4/part-49-00000.npy b/full_data/c4/part-49-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..6a91d229cf93be544a43ca28a7cf6a28d67141a4
--- /dev/null
+++ b/full_data/c4/part-49-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c63fa80590c0cf47d66e0af2d71f51eddb7e4499d5506e9edc1ce25fcacec53
+size 2147483528
diff --git a/full_data/c4/part-49-00001.csv.gz b/full_data/c4/part-49-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..4756ced738815de5a29658efc84fef1a19155ed6
--- /dev/null
+++ b/full_data/c4/part-49-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64fd5c5ead18dd45689d0d52ec112c5184225af5a61f4822c7f09d20795cd5e8
+size 68047952
diff --git a/full_data/c4/part-49-00001.npy b/full_data/c4/part-49-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..8e66421336d23fdfa0e51e6625ef6cfda6bbcc26
--- /dev/null
+++ b/full_data/c4/part-49-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3855f71103a79bf906c355cb298a2b2f0edda135a73d84895b340fbb00d1717
+size 2147483378
diff --git a/full_data/c4/part-49-00002.csv.gz b/full_data/c4/part-49-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..ce3d2b540600c93c7af2342a8017551b8d3a4bc4
--- /dev/null
+++ b/full_data/c4/part-49-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e1b3bd86d775d6343dd6b3bdcb3f02021fe70caee82c05f0793cf39a525e87
+size 68234659
diff --git a/full_data/c4/part-49-00002.npy b/full_data/c4/part-49-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..453f64168cee840083cf59002b284254137a899e
--- /dev/null
+++ b/full_data/c4/part-49-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4552c5f81678b5dc645f70e308801f27b4f84e2778ced4c30a0dd1d7cbfb0664
+size 2147482946
diff --git a/full_data/c4/part-49-00003.csv.gz b/full_data/c4/part-49-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..87ef14e89a334e49482df549f044cf4cb7a50082
--- /dev/null
+++ b/full_data/c4/part-49-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951439353da37f21f55e176e6517aca1472f673e3f4548cad6b6659396017cb8
+size 55884940
diff --git a/full_data/c4/part-49-00003.npy b/full_data/c4/part-49-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..249729c97f9d27c1f6544fd638522599358e34c2
--- /dev/null
+++ b/full_data/c4/part-49-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874baa4827f15e3577b02f1a0c8cfffc6329ca2fd6aeb59b4bd15438843b5eda
+size 1762038854
diff --git a/full_data/c4/part-50-00000.csv.gz b/full_data/c4/part-50-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..d98bfe19174139b224114fa3f81324d2da11852b
--- /dev/null
+++ b/full_data/c4/part-50-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf1f29e6c96abd676f040c48ea2615493176fc0de8ed2c685e2493c8a140fb7e
+size 67995511
diff --git a/full_data/c4/part-50-00000.npy b/full_data/c4/part-50-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..0c21b01ffa751b7d2305229dddbd11f1e1571a35
--- /dev/null
+++ b/full_data/c4/part-50-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70188b55e82d0c9ff65b063b1a5155795cf73ab7365a03c8f2107a23fab958a1
+size 2147482538
diff --git a/full_data/c4/part-50-00001.csv.gz b/full_data/c4/part-50-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..51f1db36f16ab0a09b5df8c0fab6dadd5a712305
--- /dev/null
+++ b/full_data/c4/part-50-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c44fda657883b3274956762b9f563cf73c314673eafd84aeece3bd99789e912
+size 62126413
diff --git a/full_data/c4/part-50-00001.npy b/full_data/c4/part-50-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..1294dd49ceed26c2aa20918c7ce42e0c603a924c
--- /dev/null
+++ b/full_data/c4/part-50-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7491971cb06d9524bd991243742e187584686b169dc8e9b5e88c99d902662741
+size 1957608196
diff --git a/full_data/c4/part-51-00000.csv.gz b/full_data/c4/part-51-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e7da3c5c5031f9709c28e271b2f0ac56f836e32c
--- /dev/null
+++ b/full_data/c4/part-51-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8206e30edf1b73fd2b431b6d032ea6772a4352ac0bf3d25a0846f15dbbdfefd3
+size 68124924
diff --git a/full_data/c4/part-51-00000.npy b/full_data/c4/part-51-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f0426677cffa6c17e9135357d49825bcb3ce0ad9
--- /dev/null
+++ b/full_data/c4/part-51-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e022d75e18de94b07c311ae9d74c3a4ea628f417a5d04e0c60f47e50f1b72d1f
+size 2147481592
diff --git a/full_data/c4/part-51-00001.csv.gz b/full_data/c4/part-51-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..4a9fe67f462f307233fa4e64aec912797fecf006
--- /dev/null
+++ b/full_data/c4/part-51-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb9ee19caa491097799bbf858356218a630521a68de284c11989af123061f561
+size 61995534
diff --git a/full_data/c4/part-51-00001.npy b/full_data/c4/part-51-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..09cfa32842d167dff0cddb6cf1fe31a065fc2b6f
--- /dev/null
+++ b/full_data/c4/part-51-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:147a06454eef895430ff194705b1e07d82ab9dc8de76b822ccd83a52dc275661
+size 1957286722
diff --git a/full_data/c4/part-52-00000.csv.gz b/full_data/c4/part-52-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..62df47c77a3adcf16dbdd344a247ff2ca43d2839
--- /dev/null
+++ b/full_data/c4/part-52-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a47b5d507443c155d11353aab6c67f9b8081a512e1f0f7af9b006644fcac4ea
+size 68127249
diff --git a/full_data/c4/part-52-00000.npy b/full_data/c4/part-52-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..dfa83fedf676017059bfdaf3727ba7b4f4337c38
--- /dev/null
+++ b/full_data/c4/part-52-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5dcd7b6d9ddaab70f3d17bb6abc6510d00cc7de92d6803332f3e226196f2edd
+size 2147482942
diff --git a/full_data/c4/part-52-00001.csv.gz b/full_data/c4/part-52-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..7b2c19f23f670afea23da5014be7fe54d07c4702
--- /dev/null
+++ b/full_data/c4/part-52-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31deaee958213f7966b1689ef92eb99965a31192fda01e43a3c8c61d6d802fbe
+size 68036190
diff --git a/full_data/c4/part-52-00001.npy b/full_data/c4/part-52-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..b56442a632b43943590b6b8c6f2e6aebf1e097d8
--- /dev/null
+++ b/full_data/c4/part-52-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee37f79f38d780a5644833665c8353772298e60d0baabfd420e79caf3c613a04
+size 2147483142
diff --git a/full_data/c4/part-52-00002.csv.gz b/full_data/c4/part-52-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..84e41ca926caf3996ef262e44eaaf73c751b164e
--- /dev/null
+++ b/full_data/c4/part-52-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5dafb3666af3b1eb451f7f4cb8adb09890a929dcee458fbb4206985c9ff6afc
+size 68243657
diff --git a/full_data/c4/part-52-00002.npy b/full_data/c4/part-52-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a7705bc769064ec7d5f89ee6ed13312d7e6bda9a
--- /dev/null
+++ b/full_data/c4/part-52-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9f921ce551d012cbe026666c2397e9c090a8d9c6b4026b78bfa0ec59caad56e
+size 2147483572
diff --git a/full_data/c4/part-52-00003.csv.gz b/full_data/c4/part-52-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..8bbcebfd60c43fd245b39e25d24f5679515cf014
--- /dev/null
+++ b/full_data/c4/part-52-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:446d6ff82bf1c4d898a736b0ac32578fdf7651adb946069e29d5137aaf88e203
+size 55915244
diff --git a/full_data/c4/part-52-00003.npy b/full_data/c4/part-52-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..06868a8879fdf565a9d06d38854df5126b196fdd
--- /dev/null
+++ b/full_data/c4/part-52-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:968c26e16fe1fd4202f89c17da1e4af1435a9ff3181c5a550110a00c75aafe06
+size 1764413132
diff --git a/full_data/c4/part-53-00000.csv.gz b/full_data/c4/part-53-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..6e2559066f9c57c56b0300585106d78589438b8a
--- /dev/null
+++ b/full_data/c4/part-53-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920120d74e06ceef4a6aaf480b69c6c29fc1551004b55c20bd2e31d68cc5ddec
+size 68051233
diff --git a/full_data/c4/part-53-00000.npy b/full_data/c4/part-53-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..7d35af6e7acebc41369ab26a6d853be604436156
--- /dev/null
+++ b/full_data/c4/part-53-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27c53daa01f8eca7d38d1e3da4978288efca94082489cb6b51dcb3874b4915c4
+size 2147483090
diff --git a/full_data/c4/part-53-00001.csv.gz b/full_data/c4/part-53-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..618ca37f8b8a159ec0bfe35cf3835fef8c8b0caf
--- /dev/null
+++ b/full_data/c4/part-53-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d034f0583175b0a0eff3c21c65e4b9592fc7253284584393dbe483e8f52f58a6
+size 62064782
diff --git a/full_data/c4/part-53-00001.npy b/full_data/c4/part-53-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3a5e72692ce391975b35efc25eba8f6440c86a76
--- /dev/null
+++ b/full_data/c4/part-53-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9221831c211d2d4e81f99da0e7b4d92126c6f1e22f87179d4e1c5193e6381ecf
+size 1957434560
diff --git a/full_data/c4/part-54-00000.csv.gz b/full_data/c4/part-54-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..d38ed56675aaed82b85626f3a8ff940022b51467
--- /dev/null
+++ b/full_data/c4/part-54-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:980b394d36250fcaccdba8966d3d550e6f2e64ee9ac9c0e12b598d4fe825aebd
+size 67960167
diff --git a/full_data/c4/part-54-00000.npy b/full_data/c4/part-54-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..45f1e6930275434da7192475019aa0f4f70fa299
--- /dev/null
+++ b/full_data/c4/part-54-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c280ee36ada7cd14290eefb7bfe54489c894650d901b796ede7dc6927b04f5d
+size 2147482442
diff --git a/full_data/c4/part-54-00001.csv.gz b/full_data/c4/part-54-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..08b62fdc18f31c1e288edc4cf0bc6275d6d1ff07
--- /dev/null
+++ b/full_data/c4/part-54-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b3ae2395f33dbdef46a6c3c3da5a806733fd406482afeef12eb560a4e3aa63
+size 62163679
diff --git a/full_data/c4/part-54-00001.npy b/full_data/c4/part-54-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..22e46ad4ef786ad8d2f1468fcc300386b37d3657
--- /dev/null
+++ b/full_data/c4/part-54-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:132fe1c1b2519c03fe24f76519a4b15d5c090c61a74d48269d2651af5456e0fd
+size 1965036530
diff --git a/full_data/c4/part-55-00000.csv.gz b/full_data/c4/part-55-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..2a829e758ece476e7cd2bd74427968c749fb71f9
--- /dev/null
+++ b/full_data/c4/part-55-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db2193813ec27074af3f36d9a3177ac0cd573bd9c3529a37dbe83162d9b12ee3
+size 68148169
diff --git a/full_data/c4/part-55-00000.npy b/full_data/c4/part-55-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a095b8df7366853d9a95e206c090595d0ebfd143
--- /dev/null
+++ b/full_data/c4/part-55-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00a5db8227586239492eb162934d27d9ddf8d3b2854267acfdf46870c8e60788
+size 2147483132
diff --git a/full_data/c4/part-55-00001.csv.gz b/full_data/c4/part-55-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..06a56487d76182a2d9e543830ce4064286061448
--- /dev/null
+++ b/full_data/c4/part-55-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60217bd621fa66bc61de070363a0e25892ba7a990b902b9cf26cde3be90be736
+size 68276529
diff --git a/full_data/c4/part-55-00001.npy b/full_data/c4/part-55-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..af5faf4d4e701a605d3404b28d8a035999529956
--- /dev/null
+++ b/full_data/c4/part-55-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db967801596b9ba2bae41bd5e683d38b7e70be25dd64632c3b52627ae169dcb
+size 2147482562
diff --git a/full_data/c4/part-55-00002.csv.gz b/full_data/c4/part-55-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..12585a05c525071af49f3e95b3abe0a5c3127c83
--- /dev/null
+++ b/full_data/c4/part-55-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4429ffb57f28f84ab14e8d7cab564f904b00eace7e977c4c24abca04a9d680db
+size 68009561
diff --git a/full_data/c4/part-55-00002.npy b/full_data/c4/part-55-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..1db9ffe4f06dca97be5ab26baeb173f8b6021f54
--- /dev/null
+++ b/full_data/c4/part-55-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c16e83fabe433523a655766148131004775618c97cb8f835d492456cddff64
+size 2147476904
diff --git a/full_data/c4/part-55-00003.csv.gz b/full_data/c4/part-55-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..ac13736a3dc0e0424ff5896dba5a54e4d1f03cbe
--- /dev/null
+++ b/full_data/c4/part-55-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962932411f75be57cbac55253ad9fdb7ff0484930366ce340a2bc0c7bfa33e82
+size 55921811
diff --git a/full_data/c4/part-55-00003.npy b/full_data/c4/part-55-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..4de3c979fc4571bec45a43e72d07d9007f9383d5
--- /dev/null
+++ b/full_data/c4/part-55-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:415606b249f74ae0fe21a12011b235944f2aa7b37ea6b3be54d73c3d75587557
+size 1761017278
diff --git a/full_data/c4/part-56-00000.csv.gz b/full_data/c4/part-56-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..eeec37f8717a784c5ced848ff49eb279f91ea93a
--- /dev/null
+++ b/full_data/c4/part-56-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dcd9b2d7b22b622c0504189b888cfde6f0c32bc452cbe5dc1a0bfd463c33420
+size 67908759
diff --git a/full_data/c4/part-56-00000.npy b/full_data/c4/part-56-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..de92ff93e3192e3981e936bc74023cc201020b95
--- /dev/null
+++ b/full_data/c4/part-56-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35746e09f269ad0d9bcbdd96300901285f9ef49e89b33485b4438e2e6a9c6f27
+size 2147483534
diff --git a/full_data/c4/part-56-00001.csv.gz b/full_data/c4/part-56-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..99f8e08b8dd5d73cb5cd8f11cbc1c2a7dbc8f5ba
--- /dev/null
+++ b/full_data/c4/part-56-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44431fd54950ca5d3ff293463de889584bebd260f0cf4b08fccaaaafc35fb3c9
+size 62212957
diff --git a/full_data/c4/part-56-00001.npy b/full_data/c4/part-56-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..22b3165d3938b2cf26c2708f73bd781b8ddfaafa
--- /dev/null
+++ b/full_data/c4/part-56-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c35620d2d58ad88143fb608285cb4258e26a5bc5c444d999ffe43782beae275f
+size 1968433798
diff --git a/full_data/c4/part-57-00000.csv.gz b/full_data/c4/part-57-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..b9925b4bfd8acd3fa8fc2eed2ea7027690d1bd72
--- /dev/null
+++ b/full_data/c4/part-57-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520d87c6408e721758a4d2c4347001e211134fc44e31eb8ff63515fdc84edd84
+size 68025112
diff --git a/full_data/c4/part-57-00000.npy b/full_data/c4/part-57-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..33ef6c35e0768eb5cc9a7eb40b053a128d2c194c
--- /dev/null
+++ b/full_data/c4/part-57-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812d1358bc96efc83bcaf9cbebf8385ea21d683ed5f823b0bb7f926501e5dcec
+size 2147483334
diff --git a/full_data/c4/part-57-00001.csv.gz b/full_data/c4/part-57-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..d25eee8c77d995f9fcc048ac1783c5e7a51d8507
--- /dev/null
+++ b/full_data/c4/part-57-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:714acc555eaa951d200f7dcf03dc09cd674dff48f5041cc7cdb22bb42fb50128
+size 62090460
diff --git a/full_data/c4/part-57-00001.npy b/full_data/c4/part-57-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..0ff81f81cce2ac24dbd9b47322e359c3075b8f71
--- /dev/null
+++ b/full_data/c4/part-57-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5452584b77b30a8ffbe935058a2e68e994b7072ef8bcce57357e51d7d31fa36
+size 1957218530
diff --git a/full_data/c4/part-58-00000.csv.gz b/full_data/c4/part-58-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..1b9a745ebaaad4e97a6c1a1fba28cf7512e88b79
--- /dev/null
+++ b/full_data/c4/part-58-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41aca66cc53348e30cf313e5af4238f032dc2d79d0c0dcc51c7b9e2c05386592
+size 68416296
diff --git a/full_data/c4/part-58-00000.npy b/full_data/c4/part-58-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..73331f3405d408043bcadc908556ed6c30848d28
--- /dev/null
+++ b/full_data/c4/part-58-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a29b24d396ec336b1bef39e09af55dea65470012d257d089f44c9cd62b74b91d
+size 2147483366
diff --git a/full_data/c4/part-58-00001.csv.gz b/full_data/c4/part-58-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..4724fd2aa7eab72b6e6fa7cce7e0067788c3351c
--- /dev/null
+++ b/full_data/c4/part-58-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fb59091c0330f64ebcef200d74196d7cb5cb1c0ec23aab271b917a6bf28bff2
+size 68349414
diff --git a/full_data/c4/part-58-00001.npy b/full_data/c4/part-58-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..a018496be54bd70b283dab4c5e6e27c4e09b57ff
--- /dev/null
+++ b/full_data/c4/part-58-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23fdcb58816a467c534ee3742fd7e84aade05deae5a290af3dbdfc8bb99b0bd6
+size 2147483450
diff --git a/full_data/c4/part-58-00002.csv.gz b/full_data/c4/part-58-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..4ef987bf93d3bddc205706151fff763bbe06c712
--- /dev/null
+++ b/full_data/c4/part-58-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bf71eddf86df5b1fc1404fcdd18fbd456fd1a43d5e0e7cf78b470455b96cafb
+size 68491545
diff --git a/full_data/c4/part-58-00002.npy b/full_data/c4/part-58-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..f552c22f04791640d13777e8182c9afc3d80e440
--- /dev/null
+++ b/full_data/c4/part-58-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9de3066be518dbba94a2a753685895ae107a965c6bdf1f6f0c80ae3047b1d8f9
+size 2147482972
diff --git a/full_data/c4/part-58-00003.csv.gz b/full_data/c4/part-58-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..8e604b5547c1f66087671d35177f848caa5d5545
--- /dev/null
+++ b/full_data/c4/part-58-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd0948dbf076fff5df51689b96f1d0c90a997d8986f0ee0fb8dd136a9cd0154
+size 56294192
diff --git a/full_data/c4/part-58-00003.npy b/full_data/c4/part-58-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..71249ff284b4e11ab5cf406b82519e9fd265cdb4
--- /dev/null
+++ b/full_data/c4/part-58-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc39ea0fae4385265afde423b278b083870ed549b0e2855b5503295444adb810
+size 1764258102
diff --git a/full_data/c4/part-59-00000.csv.gz b/full_data/c4/part-59-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..770c1656e821e1e067e22627d730db63e6faa236
--- /dev/null
+++ b/full_data/c4/part-59-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3134bd839e090a2798455d78739855de3b4fcd782f1bbe2b2c45a6d497f09dd2
+size 68176822
diff --git a/full_data/c4/part-59-00000.npy b/full_data/c4/part-59-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..9a327266b177763df7e8b4b1dabea20226672ee5
--- /dev/null
+++ b/full_data/c4/part-59-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22ea6e9131ee65cabab64feccff435839f62befda1b87810f007bfeec3310248
+size 2147481500
diff --git a/full_data/c4/part-59-00001.csv.gz b/full_data/c4/part-59-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..3bfd3c6dadf4b42c0fc233473ed28a807a3a6bfd
--- /dev/null
+++ b/full_data/c4/part-59-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3993b72fcca1e9e3dad9a0bed9ad3549c2badb14e5d7059e50e8c01a4df93df
+size 61942424
diff --git a/full_data/c4/part-59-00001.npy b/full_data/c4/part-59-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..32dfbe17e22ddd3ab41656470a5971d89b2ed65d
--- /dev/null
+++ b/full_data/c4/part-59-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f8a190f10a7ec9868b942c52e57a5f98a78ee1adb50859703b8f8f112df34b4
+size 1953851144
diff --git a/full_data/c4/part-60-00000.csv.gz b/full_data/c4/part-60-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..5d37b04bd75c0a87237148edaf5b3c31177aad68
--- /dev/null
+++ b/full_data/c4/part-60-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8d17ecacbcf9883c535af6a4717cff391d393df7db70fe6ba0bcb285c801fe
+size 68100794
diff --git a/full_data/c4/part-60-00000.npy b/full_data/c4/part-60-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..408b519c4c77d9efa140a082dd8b868a09b330a1
--- /dev/null
+++ b/full_data/c4/part-60-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89b0526ed314d99b156ba0d17a27c519178d356e4801dadc7332407089fed9bc
+size 2147483516
diff --git a/full_data/c4/part-60-00001.csv.gz b/full_data/c4/part-60-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e9810c021fefb8b388069be5c9b1d7d96a1ef5ca
--- /dev/null
+++ b/full_data/c4/part-60-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c639fd10e99e1825476e7b328a1ed26e03e68f0aeafdc58986c3322bbcf3eb5
+size 62017305
diff --git a/full_data/c4/part-60-00001.npy b/full_data/c4/part-60-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3566464b832a25444ee43ff0f5372b130380f823
--- /dev/null
+++ b/full_data/c4/part-60-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e347079151c75b23744cda819d5f54303a83b9e5214953854ed9b59d28fc7cc
+size 1957475764
diff --git a/full_data/c4/part-61-00000.csv.gz b/full_data/c4/part-61-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..86cb0257b2bf26062be8999004a9b4180736627d
--- /dev/null
+++ b/full_data/c4/part-61-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6b0c56c9a78fdf7a66495f11e08969a1271c1d022d583cea2f97dd7e1ce1d6d
+size 68079823
diff --git a/full_data/c4/part-61-00000.npy b/full_data/c4/part-61-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..895368d2cae6b8537a9e8b509046741d79a4f7a8
--- /dev/null
+++ b/full_data/c4/part-61-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e5f2ad7192071c4bc0cfc0b539843f8b3457d0591bffd6c83d3905d6a69fe4f
+size 2147482888
diff --git a/full_data/c4/part-61-00001.csv.gz b/full_data/c4/part-61-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..68297c5c056028cb128522b587e73219db0e673f
--- /dev/null
+++ b/full_data/c4/part-61-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91fbe54b0bf594665ccb8b356752ead521bc9d3cf92e1a225d9677defeb50bbb
+size 68164562
diff --git a/full_data/c4/part-61-00001.npy b/full_data/c4/part-61-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..cde71c3240ada3c56fb792e050a437cb3611b082
--- /dev/null
+++ b/full_data/c4/part-61-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a760e4fc3a90339401be7a2cf632976cbb68fa7645d187962388679c2d61f5d
+size 2147483486
diff --git a/full_data/c4/part-61-00002.csv.gz b/full_data/c4/part-61-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..3983688b366a14b3b5f7b192ff533d4739916edf
--- /dev/null
+++ b/full_data/c4/part-61-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc5453199cb0367f58a79b8a86d8f30805e49f0f6ecc285f952b235a14318ba7
+size 68142764
diff --git a/full_data/c4/part-61-00002.npy b/full_data/c4/part-61-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..7f6022c7bab894368b3d193726e8605705b3e46e
--- /dev/null
+++ b/full_data/c4/part-61-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b29584e65885704cf85977a7e958c909af60d6b5d04fb988448f350b7c45d59
+size 2147482238
diff --git a/full_data/c4/part-61-00003.csv.gz b/full_data/c4/part-61-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..af7d0585576c4c6c0871fda55b0374603580123e
--- /dev/null
+++ b/full_data/c4/part-61-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08bc0a4395d16daabd540a722f6a89dc4d573bf56a483bc779e9d7ebe5903f0c
+size 55965296
diff --git a/full_data/c4/part-61-00003.npy b/full_data/c4/part-61-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..e95bee230a75881d8be2ec8cff262433b982fdba
--- /dev/null
+++ b/full_data/c4/part-61-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2db4d1f066a6f549623d572fc3b069425a4c4d33c5d648a7b75ad6a9c577108
+size 1765043760
diff --git a/full_data/c4/part-62-00000.csv.gz b/full_data/c4/part-62-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..77a5717cfc7e0d2096d1e26ca1cf5791c9736d8b
--- /dev/null
+++ b/full_data/c4/part-62-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8e2b1b425af31164fbd9a90b86b7eecdde5a7d92776163d333b55d6fa92d15
+size 68101372
diff --git a/full_data/c4/part-62-00000.npy b/full_data/c4/part-62-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..13457f7ad4c5e584fdd35cf2a0116308a846f5a5
--- /dev/null
+++ b/full_data/c4/part-62-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ccf63215cb1fc3b03665b314d14340eee32c4439f0267d26729cd06b33bbb44
+size 2147483404
diff --git a/full_data/c4/part-62-00001.csv.gz b/full_data/c4/part-62-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e7edd52ac8c655ebd18f370785eec623bee1cd1b
--- /dev/null
+++ b/full_data/c4/part-62-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d456028d53f14376be70140e9da30b1854626183475fc330329aa38b49641baf
+size 62017254
diff --git a/full_data/c4/part-62-00001.npy b/full_data/c4/part-62-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..2eb4edc2da8f64ba8457b57c6592a2bcd418ee3e
--- /dev/null
+++ b/full_data/c4/part-62-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cadf3319fb5ce94500063a7ef35c4f4ba2b1c54a01ca49e02fbf5bb314730cac
+size 1957815222
diff --git a/full_data/c4/part-63-00000.csv.gz b/full_data/c4/part-63-00000.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..1b5ed20aec80bb53c21acccb59e93c1a8efea51f
--- /dev/null
+++ b/full_data/c4/part-63-00000.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22658e4b9f7d13665cb671275fb473b5e12e4f997831deac3383c9cdfdd573ed
+size 68166632
diff --git a/full_data/c4/part-63-00000.npy b/full_data/c4/part-63-00000.npy
new file mode 100644
index 0000000000000000000000000000000000000000..685657f9f5411dc2026b9b6c22b00a93b9f69af6
--- /dev/null
+++ b/full_data/c4/part-63-00000.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b248ee85eb0c4a228a5e488506af4742303667661092f5291e60d0d726f0c56b
+size 2147483614
diff --git a/full_data/c4/part-63-00001.csv.gz b/full_data/c4/part-63-00001.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..cb3a905cee1f13bbb8db1bf576d204ea19eb4c76
--- /dev/null
+++ b/full_data/c4/part-63-00001.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baa1df7502014bca628c9537b84bb2f805c3f32ffa14eb68d9b70e2d54a6babb
+size 68111098
diff --git a/full_data/c4/part-63-00001.npy b/full_data/c4/part-63-00001.npy
new file mode 100644
index 0000000000000000000000000000000000000000..bd6fef6dd6426f06fccbaa42e8805d7e9d55e842
--- /dev/null
+++ b/full_data/c4/part-63-00001.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d6790f52467a9d11170f56b94882977839aaeaf3b450dfeb3a7a529324eaa8
+size 2147483496
diff --git a/full_data/c4/part-63-00002.csv.gz b/full_data/c4/part-63-00002.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..94ebc4716449789bc9f450fcbfb7f8e19ecd0a58
--- /dev/null
+++ b/full_data/c4/part-63-00002.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2b8cf0ec53514badf7ec2e99489f165c1578fdd7944139d957ca77d96b93b9
+size 68373861
diff --git a/full_data/c4/part-63-00002.npy b/full_data/c4/part-63-00002.npy
new file mode 100644
index 0000000000000000000000000000000000000000..eb073f8b469f7ff91d27e30562d9a582774265ec
--- /dev/null
+++ b/full_data/c4/part-63-00002.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62b4221ed0dc69fb9eaad834d17bbe104aa87355f70f865aa90af319fe65362f
+size 2147483498
diff --git a/full_data/c4/part-63-00003.csv.gz b/full_data/c4/part-63-00003.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e97febeaabab364b886aee7784501b543ec80fce
--- /dev/null
+++ b/full_data/c4/part-63-00003.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:753593e79c6d946b268280a83fbed2316ced1e1069c4d8a712b00e9d22849613
+size 55704842
diff --git a/full_data/c4/part-63-00003.npy b/full_data/c4/part-63-00003.npy
new file mode 100644
index 0000000000000000000000000000000000000000..002908f248e895863ede30e646bfac88d869acfd
--- /dev/null
+++ b/full_data/c4/part-63-00003.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b8f071a9802e0f3f51fd10aa772ce80b0ac62c69593cb3967a5587a301b6774
+size 1755480532