diff --git a/.dvc/.gitignore b/.dvc/.gitignore
new file mode 100644
index 0000000..528f30c
--- /dev/null
+++ b/.dvc/.gitignore
@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache
diff --git a/.dvc/config b/.dvc/config
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/.dvc/config
diff --git a/.dvcignore b/.dvcignore
new file mode 100644
index 0000000..5197305
--- /dev/null
+++ b/.dvcignore
@@ -0,0 +1,3 @@
+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore
diff --git a/astro-ner/.gitignore b/astro-ner/.gitignore
index b694934..6bf83b8 100644
--- a/astro-ner/.gitignore
+++ b/astro-ner/.gitignore
@@ -1 +1,4 @@
-.venv
\ No newline at end of file
+.venv
+/data
+/train_data
+/astro.xlsx
diff --git a/astro-ner/astro.xlsx.dvc b/astro-ner/astro.xlsx.dvc
new file mode 100644
index 0000000..eacee15
--- /dev/null
+++ b/astro-ner/astro.xlsx.dvc
@@ -0,0 +1,5 @@
+outs:
+- md5: 7d9855c57c102f94c9dfdb250e4c8fd5
+  size: 30468
+  hash: md5
+  path: astro.xlsx
diff --git a/astro-ner/data.dvc b/astro-ner/data.dvc
new file mode 100644
index 0000000..4564392
--- /dev/null
+++ b/astro-ner/data.dvc
@@ -0,0 +1,6 @@
+outs:
+- md5: 88471bfee0fe1bae20dbf2f4ee8d367b.dir
+  size: 11885573
+  nfiles: 149
+  hash: md5
+  path: data
diff --git a/astro-ner/train_data.dvc b/astro-ner/train_data.dvc
new file mode 100644
index 0000000..ce686a5
--- /dev/null
+++ b/astro-ner/train_data.dvc
@@ -0,0 +1,6 @@
+outs:
+- md5: fe03d711910c33c0d78937afedb0b303.dir
+  size: 2952036
+  nfiles: 3
+  hash: md5
+  path: train_data