removed data files since it loads anew

data/astrophindex.faiss

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:10089ae87900eb8c9f1698c36bb5d1128d712b7b90f3f3d07f074ab130027440
-size 2163879981

data/data-00000-of-00008.arrow

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8fd656a426f8ff3d7c2bb7164154b042d50f5e5deeeb7ead12b9baee7b9d5f8d
-size 509410376

data/data-00001-of-00008.arrow

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:952f8125fc109ff15b7abbfb10ac928b6070087899e79ebbf62500b018a2bac7
-size 503809992

data/data-00002-of-00008.arrow

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b1069ba9c791822f5761b7311f69bc0323294751499988bcb3ae904b339a89dd
-size 504473320

data/data-00003-of-00008.arrow

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1f91fb8b3aed602e091b89e35fff7432d4573f5ccbdc2d5d9d19daabbacc3a5b
-size 508874456

data/data-00004-of-00008.arrow

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eb7f52083e24ef80fc12bca90c88aac3159d5479af9f29de4a7740dacb85d9d6
-size 501644912

data/data-00005-of-00008.arrow

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f77f69ede7a456f8f59873e482bf381626532b945e50b497b91834d814ba8ce2
-size 501508320

data/data-00006-of-00008.arrow

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:762b9acd3aa46c27b40af2a681b638e6ac345fbb508360c68f815e284d61f584
-size 470994224

data/data-00007-of-00008.arrow

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:58b898027e4506c6a7a0afb9bdc5e61c8df13a8d5089a68383a457dc6dea1b72
-size 497639288

data/dataset_info.json

@@ -1,169 +0,0 @@
-{
-  "builder_name": "parquet",
-  "citation": "",
-  "config_name": "default",
-  "dataset_name": "pathfinder_arxiv_data",
-  "dataset_size": 4065510154,
-  "description": "",
-  "download_checksums": {
-    "hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00000-of-00008.parquet": {
-      "num_bytes": 406754152,
-      "checksum": null
-    },
-    "hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00001-of-00008.parquet": {
-      "num_bytes": 405109745,
-      "checksum": null
-    },
-    "hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00002-of-00008.parquet": {
-      "num_bytes": 405466052,
-      "checksum": null
-    },
-    "hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00003-of-00008.parquet": {
-      "num_bytes": 406784839,
-      "checksum": null
-    },
-    "hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00004-of-00008.parquet": {
-      "num_bytes": 404752067,
-      "checksum": null
-    },
-    "hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00005-of-00008.parquet": {
-      "num_bytes": 404624503,
-      "checksum": null
-    },
-    "hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00006-of-00008.parquet": {
-      "num_bytes": 392634525,
-      "checksum": null
-    },
-    "hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00007-of-00008.parquet": {
-      "num_bytes": 397101125,
-      "checksum": null
-    }
-  },
-  "download_size": 3223227008,
-  "features": {
-    "ads_id": {
-      "dtype": "string",
-      "_type": "Value"
-    },
-    "arxiv_id": {
-      "dtype": "string",
-      "_type": "Value"
-    },
-    "title": {
-      "dtype": "string",
-      "_type": "Value"
-    },
-    "abstract": {
-      "dtype": "string",
-      "_type": "Value"
-    },
-    "embed": {
-      "feature": {
-        "dtype": "float32",
-        "_type": "Value"
-      },
-      "_type": "Sequence"
-    },
-    "umap_x": {
-      "dtype": "float32",
-      "_type": "Value"
-    },
-    "umap_y": {
-      "dtype": "float32",
-      "_type": "Value"
-    },
-    "date": {
-      "dtype": "date32",
-      "_type": "Value"
-    },
-    "cites": {
-      "dtype": "int64",
-      "_type": "Value"
-    },
-    "bibcode": {
-      "dtype": "string",
-      "_type": "Value"
-    },
-    "keywords": {
-      "feature": {
-        "dtype": "string",
-        "_type": "Value"
-      },
-      "_type": "Sequence"
-    },
-    "ads_keywords": {
-      "feature": {
-        "dtype": "string",
-        "_type": "Value"
-      },
-      "_type": "Sequence"
-    },
-    "read_count": {
-      "dtype": "int64",
-      "_type": "Value"
-    },
-    "doi": {
-      "feature": {
-        "dtype": "string",
-        "_type": "Value"
-      },
-      "_type": "Sequence"
-    },
-    "authors": {
-      "feature": {
-        "dtype": "string",
-        "_type": "Value"
-      },
-      "_type": "Sequence"
-    },
-    "aff": {
-      "feature": {
-        "dtype": "string",
-        "_type": "Value"
-      },
-      "_type": "Sequence"
-    },
-    "cite_bibcodes": {
-      "feature": {
-        "dtype": "string",
-        "_type": "Value"
-      },
-      "_type": "Sequence"
-    },
-    "ref_bibcodes": {
-      "feature": {
-        "dtype": "string",
-        "_type": "Value"
-      },
-      "_type": "Sequence"
-    }
-  },
-  "homepage": "",
-  "license": "",
-  "size_in_bytes": 7288737162,
-  "splits": {
-    "train": {
-      "name": "train",
-      "num_bytes": 4065510154,
-      "num_examples": 352194,
-      "shard_lengths": [
-        43000,
-        43025,
-        43025,
-        43024,
-        44024,
-        44024,
-        46024,
-        44024,
-        2024
-      ],
-      "dataset_name": "pathfinder_arxiv_data"
-    }
-  },
-  "version": {
-    "version_str": "0.0.0",
-    "major": 0,
-    "minor": 0,
-    "patch": 0
-  }
-}

data/state.json

@@ -1,34 +0,0 @@
-{
-  "_data_files": [
-    {
-      "filename": "data-00000-of-00008.arrow"
-    },
-    {
-      "filename": "data-00001-of-00008.arrow"
-    },
-    {
-      "filename": "data-00002-of-00008.arrow"
-    },
-    {
-      "filename": "data-00003-of-00008.arrow"
-    },
-    {
-      "filename": "data-00004-of-00008.arrow"
-    },
-    {
-      "filename": "data-00005-of-00008.arrow"
-    },
-    {
-      "filename": "data-00006-of-00008.arrow"
-    },
-    {
-      "filename": "data-00007-of-00008.arrow"
-    }
-  ],
-  "_fingerprint": "216019f3026e4d55",
-  "_format_columns": null,
-  "_format_kwargs": {},
-  "_format_type": null,
-  "_output_all_columns": false,
-  "_split": "train"
-}