Spaces:
Running
Running
Upload folder using huggingface_hub
Browse files- .gitattributes +8 -0
- data/datasets/lilac/wikitext-2-raw-v1/config.yml +21 -0
- data/datasets/lilac/wikitext-2-raw-v1/data-00000-of-00001.parquet +3 -0
- data/datasets/lilac/wikitext-2-raw-v1/manifest.json +18 -0
- data/datasets/lilac/wikitext-2-raw-v1/text/gte-small/hnsw.hnswlib.bin +3 -0
- data/datasets/lilac/wikitext-2-raw-v1/text/gte-small/hnsw.lookup.pkl +3 -0
- data/datasets/lilac/wikitext-2-raw-v1/text/gte-small/signal_manifest.json +35 -0
- data/datasets/lilac/wikitext-2-raw-v1/text/gte-small/spans.pkl +3 -0
- data/datasets/lilac/wikitext-2-raw-v1/text/lang_detection/data-00000-of-00001.parquet +3 -0
- data/datasets/lilac/wikitext-2-raw-v1/text/lang_detection/signal_manifest.json +31 -0
- data/datasets/lilac/wikitext-2-raw-v1/text/near_dup/data-00000-of-00001.parquet +3 -0
- data/datasets/lilac/wikitext-2-raw-v1/text/near_dup/signal_manifest.json +36 -0
- data/datasets/lilac/wikitext-2-raw-v1/text/pii/data-00000-of-00001.parquet +3 -0
- data/datasets/lilac/wikitext-2-raw-v1/text/pii/signal_manifest.json +45 -0
- data/datasets/lilac/wikitext-2-raw-v1/text/text_statistics/data-00000-of-00001.parquet +3 -0
- data/datasets/lilac/wikitext-2-raw-v1/text/text_statistics/signal_manifest.json +59 -0
.gitattributes
CHANGED
@@ -94,3 +94,11 @@ data/datasets/lilac/OpenOrca-100k/response/lang_detection/data-00000-of-00001.pa
|
|
94 |
data/datasets/lilac/OpenOrca-100k/response/near_dup/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
|
95 |
data/datasets/lilac/OpenOrca-100k/response/pii/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
|
96 |
data/datasets/lilac/OpenOrca-100k/response/text_statistics/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
94 |
data/datasets/lilac/OpenOrca-100k/response/near_dup/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
|
95 |
data/datasets/lilac/OpenOrca-100k/response/pii/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
|
96 |
data/datasets/lilac/OpenOrca-100k/response/text_statistics/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
|
97 |
+
data/datasets/lilac/wikitext-2-raw-v1/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
|
98 |
+
data/datasets/lilac/wikitext-2-raw-v1/text/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
|
99 |
+
data/datasets/lilac/wikitext-2-raw-v1/text/gte-small/hnsw.lookup.pkl filter=lfs diff=lfs merge=lfs -text
|
100 |
+
data/datasets/lilac/wikitext-2-raw-v1/text/gte-small/spans.pkl filter=lfs diff=lfs merge=lfs -text
|
101 |
+
data/datasets/lilac/wikitext-2-raw-v1/text/lang_detection/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
|
102 |
+
data/datasets/lilac/wikitext-2-raw-v1/text/near_dup/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
|
103 |
+
data/datasets/lilac/wikitext-2-raw-v1/text/pii/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
|
104 |
+
data/datasets/lilac/wikitext-2-raw-v1/text/text_statistics/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
|
data/datasets/lilac/wikitext-2-raw-v1/config.yml
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
embeddings:
|
2 |
+
- {embedding: gte-small, path: text}
|
3 |
+
name: wikitext-2-raw-v1
|
4 |
+
namespace: local
|
5 |
+
settings:
|
6 |
+
preferred_embedding: gte-small
|
7 |
+
ui:
|
8 |
+
media_paths: [text]
|
9 |
+
signals:
|
10 |
+
- path: text
|
11 |
+
signal: {signal_name: pii}
|
12 |
+
- path: text
|
13 |
+
signal: {signal_name: near_dup}
|
14 |
+
- path: text
|
15 |
+
signal: {signal_name: lang_detection}
|
16 |
+
- path: text
|
17 |
+
signal: {signal_name: text_statistics}
|
18 |
+
- path: text
|
19 |
+
signal: {signal_name: spacy_ner}
|
20 |
+
source: {config_name: wikitext-2-raw-v1, dataset_name: wikitext, source_name: huggingface}
|
21 |
+
tags: [machine-learning]
|
data/datasets/lilac/wikitext-2-raw-v1/data-00000-of-00001.parquet
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d2722d7f4c6b75fdd39f4477d67ed046ab1da08f1fa6d757109d8df77a1a4c2
|
3 |
+
size 9171984
|
data/datasets/lilac/wikitext-2-raw-v1/manifest.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"files": [
|
3 |
+
"data-00000-of-00001.parquet"
|
4 |
+
],
|
5 |
+
"data_schema": {
|
6 |
+
"fields": {
|
7 |
+
"text": {
|
8 |
+
"dtype": "string"
|
9 |
+
},
|
10 |
+
"__hfsplit__": {
|
11 |
+
"dtype": "string"
|
12 |
+
},
|
13 |
+
"__rowid__": {
|
14 |
+
"dtype": "string"
|
15 |
+
}
|
16 |
+
}
|
17 |
+
}
|
18 |
+
}
|
data/datasets/lilac/wikitext-2-raw-v1/text/gte-small/hnsw.hnswlib.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bf347d16e631a3dce6ae96921cebc51d7c2547757dfe9922fdb771eebbbfac7
|
3 |
+
size 91233592
|
data/datasets/lilac/wikitext-2-raw-v1/text/gte-small/hnsw.lookup.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6de9264ae1f50b8dd78b4fec2601cd88625cfe253eaab24542890a870ecd900
|
3 |
+
size 1848900
|
data/datasets/lilac/wikitext-2-raw-v1/text/gte-small/signal_manifest.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"files": [],
|
3 |
+
"parquet_id": "gte-small(text)",
|
4 |
+
"data_schema": {
|
5 |
+
"fields": {
|
6 |
+
"__rowid__": {
|
7 |
+
"dtype": "string"
|
8 |
+
},
|
9 |
+
"text": {
|
10 |
+
"fields": {
|
11 |
+
"gte-small": {
|
12 |
+
"repeated_field": {
|
13 |
+
"fields": {
|
14 |
+
"embedding": {
|
15 |
+
"dtype": "embedding"
|
16 |
+
}
|
17 |
+
},
|
18 |
+
"dtype": "string_span"
|
19 |
+
},
|
20 |
+
"signal": {
|
21 |
+
"signal_name": "gte-small"
|
22 |
+
}
|
23 |
+
}
|
24 |
+
}
|
25 |
+
}
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"signal": {
|
29 |
+
"signal_name": "gte-small"
|
30 |
+
},
|
31 |
+
"enriched_path": [
|
32 |
+
"text"
|
33 |
+
],
|
34 |
+
"vector_store": "hnsw"
|
35 |
+
}
|
data/datasets/lilac/wikitext-2-raw-v1/text/gte-small/spans.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:064d18ca7f0f3b021ebfa93323bcbe9f50271da2ea2234393581a8113322683a
|
3 |
+
size 1629720
|
data/datasets/lilac/wikitext-2-raw-v1/text/lang_detection/data-00000-of-00001.parquet
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68e4d6290a46a7dac484299be15b8536324cb677ced9721934bd150a277ddaf9
|
3 |
+
size 1532348
|
data/datasets/lilac/wikitext-2-raw-v1/text/lang_detection/signal_manifest.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"files": [
|
3 |
+
"data-00000-of-00001.parquet"
|
4 |
+
],
|
5 |
+
"parquet_id": "lang_detection(text)",
|
6 |
+
"data_schema": {
|
7 |
+
"fields": {
|
8 |
+
"__rowid__": {
|
9 |
+
"dtype": "string"
|
10 |
+
},
|
11 |
+
"text": {
|
12 |
+
"fields": {
|
13 |
+
"lang_detection": {
|
14 |
+
"dtype": "string",
|
15 |
+
"signal": {
|
16 |
+
"split_by_paragraph": false,
|
17 |
+
"signal_name": "lang_detection"
|
18 |
+
}
|
19 |
+
}
|
20 |
+
}
|
21 |
+
}
|
22 |
+
}
|
23 |
+
},
|
24 |
+
"signal": {
|
25 |
+
"split_by_paragraph": false,
|
26 |
+
"signal_name": "lang_detection"
|
27 |
+
},
|
28 |
+
"enriched_path": [
|
29 |
+
"text"
|
30 |
+
]
|
31 |
+
}
|
data/datasets/lilac/wikitext-2-raw-v1/text/near_dup/data-00000-of-00001.parquet
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f316a8a3f031470cf9fa99475b81a04e962f2da7704d61de8a44089bbf7e59b
|
3 |
+
size 1703637
|
data/datasets/lilac/wikitext-2-raw-v1/text/near_dup/signal_manifest.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"files": [
|
3 |
+
"data-00000-of-00001.parquet"
|
4 |
+
],
|
5 |
+
"parquet_id": "near_dup(text)",
|
6 |
+
"data_schema": {
|
7 |
+
"fields": {
|
8 |
+
"__rowid__": {
|
9 |
+
"dtype": "string"
|
10 |
+
},
|
11 |
+
"text": {
|
12 |
+
"fields": {
|
13 |
+
"near_dup": {
|
14 |
+
"fields": {
|
15 |
+
"cluster_id": {
|
16 |
+
"dtype": "uint32",
|
17 |
+
"categorical": true
|
18 |
+
}
|
19 |
+
},
|
20 |
+
"signal": {
|
21 |
+
"threshold": 0.85,
|
22 |
+
"signal_name": "near_dup"
|
23 |
+
}
|
24 |
+
}
|
25 |
+
}
|
26 |
+
}
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"signal": {
|
30 |
+
"threshold": 0.85,
|
31 |
+
"signal_name": "near_dup"
|
32 |
+
},
|
33 |
+
"enriched_path": [
|
34 |
+
"text"
|
35 |
+
]
|
36 |
+
}
|
data/datasets/lilac/wikitext-2-raw-v1/text/pii/data-00000-of-00001.parquet
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb257c0e65788f446b23d8f389db299c51a896baf0dcbd4d37114b625868f0ad
|
3 |
+
size 1517126
|
data/datasets/lilac/wikitext-2-raw-v1/text/pii/signal_manifest.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"files": [
|
3 |
+
"data-00000-of-00001.parquet"
|
4 |
+
],
|
5 |
+
"parquet_id": "pii(text)",
|
6 |
+
"data_schema": {
|
7 |
+
"fields": {
|
8 |
+
"__rowid__": {
|
9 |
+
"dtype": "string"
|
10 |
+
},
|
11 |
+
"text": {
|
12 |
+
"fields": {
|
13 |
+
"pii": {
|
14 |
+
"fields": {
|
15 |
+
"emails": {
|
16 |
+
"repeated_field": {
|
17 |
+
"dtype": "string_span"
|
18 |
+
}
|
19 |
+
},
|
20 |
+
"ip_addresses": {
|
21 |
+
"repeated_field": {
|
22 |
+
"dtype": "string_span"
|
23 |
+
}
|
24 |
+
},
|
25 |
+
"secrets": {
|
26 |
+
"repeated_field": {
|
27 |
+
"dtype": "string_span"
|
28 |
+
}
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"signal": {
|
32 |
+
"signal_name": "pii"
|
33 |
+
}
|
34 |
+
}
|
35 |
+
}
|
36 |
+
}
|
37 |
+
}
|
38 |
+
},
|
39 |
+
"signal": {
|
40 |
+
"signal_name": "pii"
|
41 |
+
},
|
42 |
+
"enriched_path": [
|
43 |
+
"text"
|
44 |
+
]
|
45 |
+
}
|
data/datasets/lilac/wikitext-2-raw-v1/text/text_statistics/data-00000-of-00001.parquet
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96b6d56208f0c74e7c9bc1d858ebabaae941eaf2c95cdf9207a7bdd1418a59ce
|
3 |
+
size 1827010
|
data/datasets/lilac/wikitext-2-raw-v1/text/text_statistics/signal_manifest.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"files": [
|
3 |
+
"data-00000-of-00001.parquet"
|
4 |
+
],
|
5 |
+
"parquet_id": "text_statistics(text)",
|
6 |
+
"data_schema": {
|
7 |
+
"fields": {
|
8 |
+
"__rowid__": {
|
9 |
+
"dtype": "string"
|
10 |
+
},
|
11 |
+
"text": {
|
12 |
+
"fields": {
|
13 |
+
"text_statistics": {
|
14 |
+
"fields": {
|
15 |
+
"num_characters": {
|
16 |
+
"dtype": "int32"
|
17 |
+
},
|
18 |
+
"readability": {
|
19 |
+
"dtype": "float32"
|
20 |
+
},
|
21 |
+
"log(type_token_ratio)": {
|
22 |
+
"dtype": "float32"
|
23 |
+
},
|
24 |
+
"frac_non_ascii": {
|
25 |
+
"dtype": "float32",
|
26 |
+
"bins": [
|
27 |
+
[
|
28 |
+
"Low",
|
29 |
+
null,
|
30 |
+
0.15
|
31 |
+
],
|
32 |
+
[
|
33 |
+
"Medium",
|
34 |
+
0.15,
|
35 |
+
0.3
|
36 |
+
],
|
37 |
+
[
|
38 |
+
"High",
|
39 |
+
0.3,
|
40 |
+
null
|
41 |
+
]
|
42 |
+
]
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"signal": {
|
46 |
+
"signal_name": "text_statistics"
|
47 |
+
}
|
48 |
+
}
|
49 |
+
}
|
50 |
+
}
|
51 |
+
}
|
52 |
+
},
|
53 |
+
"signal": {
|
54 |
+
"signal_name": "text_statistics"
|
55 |
+
},
|
56 |
+
"enriched_path": [
|
57 |
+
"text"
|
58 |
+
]
|
59 |
+
}
|