Spaces:
Runtime error
Runtime error
kartheikiyer
commited on
Commit
Β·
88c92ac
1
Parent(s):
2007c08
removed data files since it loads anew
Browse files- data/astrophindex.faiss +0 -3
- data/data-00000-of-00008.arrow +0 -3
- data/data-00001-of-00008.arrow +0 -3
- data/data-00002-of-00008.arrow +0 -3
- data/data-00003-of-00008.arrow +0 -3
- data/data-00004-of-00008.arrow +0 -3
- data/data-00005-of-00008.arrow +0 -3
- data/data-00006-of-00008.arrow +0 -3
- data/data-00007-of-00008.arrow +0 -3
- data/dataset_info.json +0 -169
- data/state.json +0 -34
data/astrophindex.faiss
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:10089ae87900eb8c9f1698c36bb5d1128d712b7b90f3f3d07f074ab130027440
|
| 3 |
-
size 2163879981
|
|
|
|
|
|
|
|
|
|
|
|
data/data-00000-of-00008.arrow
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8fd656a426f8ff3d7c2bb7164154b042d50f5e5deeeb7ead12b9baee7b9d5f8d
|
| 3 |
-
size 509410376
|
|
|
|
|
|
|
|
|
|
|
|
data/data-00001-of-00008.arrow
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:952f8125fc109ff15b7abbfb10ac928b6070087899e79ebbf62500b018a2bac7
|
| 3 |
-
size 503809992
|
|
|
|
|
|
|
|
|
|
|
|
data/data-00002-of-00008.arrow
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b1069ba9c791822f5761b7311f69bc0323294751499988bcb3ae904b339a89dd
|
| 3 |
-
size 504473320
|
|
|
|
|
|
|
|
|
|
|
|
data/data-00003-of-00008.arrow
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1f91fb8b3aed602e091b89e35fff7432d4573f5ccbdc2d5d9d19daabbacc3a5b
|
| 3 |
-
size 508874456
|
|
|
|
|
|
|
|
|
|
|
|
data/data-00004-of-00008.arrow
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:eb7f52083e24ef80fc12bca90c88aac3159d5479af9f29de4a7740dacb85d9d6
|
| 3 |
-
size 501644912
|
|
|
|
|
|
|
|
|
|
|
|
data/data-00005-of-00008.arrow
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f77f69ede7a456f8f59873e482bf381626532b945e50b497b91834d814ba8ce2
|
| 3 |
-
size 501508320
|
|
|
|
|
|
|
|
|
|
|
|
data/data-00006-of-00008.arrow
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:762b9acd3aa46c27b40af2a681b638e6ac345fbb508360c68f815e284d61f584
|
| 3 |
-
size 470994224
|
|
|
|
|
|
|
|
|
|
|
|
data/data-00007-of-00008.arrow
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:58b898027e4506c6a7a0afb9bdc5e61c8df13a8d5089a68383a457dc6dea1b72
|
| 3 |
-
size 497639288
|
|
|
|
|
|
|
|
|
|
|
|
data/dataset_info.json
DELETED
|
@@ -1,169 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"builder_name": "parquet",
|
| 3 |
-
"citation": "",
|
| 4 |
-
"config_name": "default",
|
| 5 |
-
"dataset_name": "pathfinder_arxiv_data",
|
| 6 |
-
"dataset_size": 4065510154,
|
| 7 |
-
"description": "",
|
| 8 |
-
"download_checksums": {
|
| 9 |
-
"hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00000-of-00008.parquet": {
|
| 10 |
-
"num_bytes": 406754152,
|
| 11 |
-
"checksum": null
|
| 12 |
-
},
|
| 13 |
-
"hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00001-of-00008.parquet": {
|
| 14 |
-
"num_bytes": 405109745,
|
| 15 |
-
"checksum": null
|
| 16 |
-
},
|
| 17 |
-
"hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00002-of-00008.parquet": {
|
| 18 |
-
"num_bytes": 405466052,
|
| 19 |
-
"checksum": null
|
| 20 |
-
},
|
| 21 |
-
"hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00003-of-00008.parquet": {
|
| 22 |
-
"num_bytes": 406784839,
|
| 23 |
-
"checksum": null
|
| 24 |
-
},
|
| 25 |
-
"hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00004-of-00008.parquet": {
|
| 26 |
-
"num_bytes": 404752067,
|
| 27 |
-
"checksum": null
|
| 28 |
-
},
|
| 29 |
-
"hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00005-of-00008.parquet": {
|
| 30 |
-
"num_bytes": 404624503,
|
| 31 |
-
"checksum": null
|
| 32 |
-
},
|
| 33 |
-
"hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00006-of-00008.parquet": {
|
| 34 |
-
"num_bytes": 392634525,
|
| 35 |
-
"checksum": null
|
| 36 |
-
},
|
| 37 |
-
"hf://datasets/kiyer/pathfinder_arxiv_data@1a8eaa7eef5a503386a1487e20f13bedba605245/data/train-00007-of-00008.parquet": {
|
| 38 |
-
"num_bytes": 397101125,
|
| 39 |
-
"checksum": null
|
| 40 |
-
}
|
| 41 |
-
},
|
| 42 |
-
"download_size": 3223227008,
|
| 43 |
-
"features": {
|
| 44 |
-
"ads_id": {
|
| 45 |
-
"dtype": "string",
|
| 46 |
-
"_type": "Value"
|
| 47 |
-
},
|
| 48 |
-
"arxiv_id": {
|
| 49 |
-
"dtype": "string",
|
| 50 |
-
"_type": "Value"
|
| 51 |
-
},
|
| 52 |
-
"title": {
|
| 53 |
-
"dtype": "string",
|
| 54 |
-
"_type": "Value"
|
| 55 |
-
},
|
| 56 |
-
"abstract": {
|
| 57 |
-
"dtype": "string",
|
| 58 |
-
"_type": "Value"
|
| 59 |
-
},
|
| 60 |
-
"embed": {
|
| 61 |
-
"feature": {
|
| 62 |
-
"dtype": "float32",
|
| 63 |
-
"_type": "Value"
|
| 64 |
-
},
|
| 65 |
-
"_type": "Sequence"
|
| 66 |
-
},
|
| 67 |
-
"umap_x": {
|
| 68 |
-
"dtype": "float32",
|
| 69 |
-
"_type": "Value"
|
| 70 |
-
},
|
| 71 |
-
"umap_y": {
|
| 72 |
-
"dtype": "float32",
|
| 73 |
-
"_type": "Value"
|
| 74 |
-
},
|
| 75 |
-
"date": {
|
| 76 |
-
"dtype": "date32",
|
| 77 |
-
"_type": "Value"
|
| 78 |
-
},
|
| 79 |
-
"cites": {
|
| 80 |
-
"dtype": "int64",
|
| 81 |
-
"_type": "Value"
|
| 82 |
-
},
|
| 83 |
-
"bibcode": {
|
| 84 |
-
"dtype": "string",
|
| 85 |
-
"_type": "Value"
|
| 86 |
-
},
|
| 87 |
-
"keywords": {
|
| 88 |
-
"feature": {
|
| 89 |
-
"dtype": "string",
|
| 90 |
-
"_type": "Value"
|
| 91 |
-
},
|
| 92 |
-
"_type": "Sequence"
|
| 93 |
-
},
|
| 94 |
-
"ads_keywords": {
|
| 95 |
-
"feature": {
|
| 96 |
-
"dtype": "string",
|
| 97 |
-
"_type": "Value"
|
| 98 |
-
},
|
| 99 |
-
"_type": "Sequence"
|
| 100 |
-
},
|
| 101 |
-
"read_count": {
|
| 102 |
-
"dtype": "int64",
|
| 103 |
-
"_type": "Value"
|
| 104 |
-
},
|
| 105 |
-
"doi": {
|
| 106 |
-
"feature": {
|
| 107 |
-
"dtype": "string",
|
| 108 |
-
"_type": "Value"
|
| 109 |
-
},
|
| 110 |
-
"_type": "Sequence"
|
| 111 |
-
},
|
| 112 |
-
"authors": {
|
| 113 |
-
"feature": {
|
| 114 |
-
"dtype": "string",
|
| 115 |
-
"_type": "Value"
|
| 116 |
-
},
|
| 117 |
-
"_type": "Sequence"
|
| 118 |
-
},
|
| 119 |
-
"aff": {
|
| 120 |
-
"feature": {
|
| 121 |
-
"dtype": "string",
|
| 122 |
-
"_type": "Value"
|
| 123 |
-
},
|
| 124 |
-
"_type": "Sequence"
|
| 125 |
-
},
|
| 126 |
-
"cite_bibcodes": {
|
| 127 |
-
"feature": {
|
| 128 |
-
"dtype": "string",
|
| 129 |
-
"_type": "Value"
|
| 130 |
-
},
|
| 131 |
-
"_type": "Sequence"
|
| 132 |
-
},
|
| 133 |
-
"ref_bibcodes": {
|
| 134 |
-
"feature": {
|
| 135 |
-
"dtype": "string",
|
| 136 |
-
"_type": "Value"
|
| 137 |
-
},
|
| 138 |
-
"_type": "Sequence"
|
| 139 |
-
}
|
| 140 |
-
},
|
| 141 |
-
"homepage": "",
|
| 142 |
-
"license": "",
|
| 143 |
-
"size_in_bytes": 7288737162,
|
| 144 |
-
"splits": {
|
| 145 |
-
"train": {
|
| 146 |
-
"name": "train",
|
| 147 |
-
"num_bytes": 4065510154,
|
| 148 |
-
"num_examples": 352194,
|
| 149 |
-
"shard_lengths": [
|
| 150 |
-
43000,
|
| 151 |
-
43025,
|
| 152 |
-
43025,
|
| 153 |
-
43024,
|
| 154 |
-
44024,
|
| 155 |
-
44024,
|
| 156 |
-
46024,
|
| 157 |
-
44024,
|
| 158 |
-
2024
|
| 159 |
-
],
|
| 160 |
-
"dataset_name": "pathfinder_arxiv_data"
|
| 161 |
-
}
|
| 162 |
-
},
|
| 163 |
-
"version": {
|
| 164 |
-
"version_str": "0.0.0",
|
| 165 |
-
"major": 0,
|
| 166 |
-
"minor": 0,
|
| 167 |
-
"patch": 0
|
| 168 |
-
}
|
| 169 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
data/state.json
DELETED
|
@@ -1,34 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_data_files": [
|
| 3 |
-
{
|
| 4 |
-
"filename": "data-00000-of-00008.arrow"
|
| 5 |
-
},
|
| 6 |
-
{
|
| 7 |
-
"filename": "data-00001-of-00008.arrow"
|
| 8 |
-
},
|
| 9 |
-
{
|
| 10 |
-
"filename": "data-00002-of-00008.arrow"
|
| 11 |
-
},
|
| 12 |
-
{
|
| 13 |
-
"filename": "data-00003-of-00008.arrow"
|
| 14 |
-
},
|
| 15 |
-
{
|
| 16 |
-
"filename": "data-00004-of-00008.arrow"
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"filename": "data-00005-of-00008.arrow"
|
| 20 |
-
},
|
| 21 |
-
{
|
| 22 |
-
"filename": "data-00006-of-00008.arrow"
|
| 23 |
-
},
|
| 24 |
-
{
|
| 25 |
-
"filename": "data-00007-of-00008.arrow"
|
| 26 |
-
}
|
| 27 |
-
],
|
| 28 |
-
"_fingerprint": "216019f3026e4d55",
|
| 29 |
-
"_format_columns": null,
|
| 30 |
-
"_format_kwargs": {},
|
| 31 |
-
"_format_type": null,
|
| 32 |
-
"_output_all_columns": false,
|
| 33 |
-
"_split": "train"
|
| 34 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|