Hugging Face's logo

asprenger
/
wikipedia-20220301.simple-embeddings

Model card Files Community
asprenger commited on
Commit
a2c7cc1
•
1 Parent(s): 733c531

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. 10_000000_000000.parquet +3 -0
  2. 10_000001_000000.parquet +3 -0
  3. 10_000002_000000.parquet +3 -0
  4. 10_000003_000000.parquet +3 -0
  5. 10_000004_000000.parquet +3 -0
  6. 10_000005_000000.parquet +3 -0
  7. 10_000006_000000.parquet +3 -0
  8. 10_000007_000000.parquet +3 -0
  9. 10_000008_000000.parquet +3 -0
  10. 10_000009_000000.parquet +3 -0
  11. _SUCCESS +0 -0
  12. _metadata.json +10 -0
10_000000_000000.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f917f2a617c9d325ad4596fca7323cf0484d8d609cb8c854644a8340653d1006
3
+ size 124574077
10_000001_000000.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ab215a69f2657b7cceb3177a240f8e8a0e57ee35ae25482c10b0582f6d9165c
3
+ size 122805994
10_000002_000000.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f520193277de65fe073701c49ffe1da2a502eee7907e544919dfa3825f7b1dc
3
+ size 119791695
10_000003_000000.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b11ee68fc2dc73c06355e94be5cd758ddd7dfb3dab69d1ff5ded1fea40c9761a
3
+ size 120631739
10_000004_000000.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad283e302c6fce4711b6203adda19b4210ceba6b19761ac3c28339785b07b618
3
+ size 120586678
10_000005_000000.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0cc647f59ed92443b59d89449f82a6925cf9b74c66ecc67f291a300d3915b89
3
+ size 118960975
10_000006_000000.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d071955b4e80e86b70885725f9fba62f973e68eaf1f7e310d2c9022a2865636f
3
+ size 119567408
10_000007_000000.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6907b5654dcec6f5135140f07a3dc4c3fdf3bdf6a5c732a81ae558e4df11d5d2
3
+ size 117625753
10_000008_000000.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34a7fb1b0ee1f7477cd6236048c1d49b5ceddcb893b898ac521b11be9d4f8fc1
3
+ size 116169239
10_000009_000000.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d557f340218d13471b91c297df153e6e6a7ab8d2af7b56976a19b396b2e458e7
3
+ size 117172502
_SUCCESS ADDED
File without changes
_metadata.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": "wikipedia",
3
+ "dataset_subset": "20220301.simple",
4
+ "dataset_size": null,
5
+ "embedding_model": "sentence-transformers/multi-qa-mpnet-base-dot-v1",
6
+ "chunk_size": 500,
7
+ "chunk_overlap": 50,
8
+ "min_doc_size": 50,
9
+ "num_chunks": 225419
10
+ }