Commit
•
30c7935
1
Parent(s):
5e0e08e
Add model
Browse files- .gitattributes +3 -0
- README.md +20 -0
- config.json +30 -0
- documents +3 -0
- embeddings +3 -0
- graph +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
documents filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
embeddings filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
graph filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
inference: false
|
| 3 |
+
language: en
|
| 4 |
+
license:
|
| 5 |
+
- cc-by-sa-3.0
|
| 6 |
+
- gfdl
|
| 7 |
+
library_name: txtai
|
| 8 |
+
tags:
|
| 9 |
+
- sentence-similarity
|
| 10 |
+
datasets:
|
| 11 |
+
- NeuML/wikipedia-20240101
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Wikipedia txtai embeddings slim
|
| 15 |
+
|
| 16 |
+
This is a [txtai](https://github.com/neuml/txtai) embeddings index for the [English edition of Wikipedia](https://en.wikipedia.org/).
|
| 17 |
+
|
| 18 |
+
The slim version has the `100K most popular` Wikipedia pages ranked by page views. This embeddings index also has graph indexing enabled, which enables using this as a source for GraphRAG.
|
| 19 |
+
|
| 20 |
+
See the [txtai-wikipedia](https://hf.co/models/neuml/txtai-wikipedia) model page for additional information on this datasource.
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"autoid": "uuid5",
|
| 3 |
+
"path": "intfloat/e5-base",
|
| 4 |
+
"instructions": {
|
| 5 |
+
"query": "query: ",
|
| 6 |
+
"data": "passage: "
|
| 7 |
+
},
|
| 8 |
+
"content": true,
|
| 9 |
+
"faiss": {
|
| 10 |
+
"quantize": true
|
| 11 |
+
},
|
| 12 |
+
"graph": {
|
| 13 |
+
"approximate": false,
|
| 14 |
+
"topics": {},
|
| 15 |
+
"backend": "networkx"
|
| 16 |
+
},
|
| 17 |
+
"dimensions": 768,
|
| 18 |
+
"backend": "faiss",
|
| 19 |
+
"offset": 100000,
|
| 20 |
+
"build": {
|
| 21 |
+
"create": "2024-07-24T17:10:13Z",
|
| 22 |
+
"python": "3.8.19",
|
| 23 |
+
"settings": {
|
| 24 |
+
"components": "IVF1265,SQ8"
|
| 25 |
+
},
|
| 26 |
+
"system": "Linux (x86_64)",
|
| 27 |
+
"txtai": "7.3.0"
|
| 28 |
+
},
|
| 29 |
+
"update": "2024-07-24T17:10:13Z"
|
| 30 |
+
}
|
documents
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:112a7f34d271a030e0a87694d6521fa1589878f48cb49f8f678383ca6f733cf3
|
| 3 |
+
size 119484416
|
embeddings
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9aba0c30f7e49dabde924812d35832ee354945e8785b29d2f4e3179b62031c8
|
| 3 |
+
size 81502528
|
graph
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0ea98eebb9bb8eb04cda254958576118a86386067b50d9086253deb5c689f25
|
| 3 |
+
size 82165760
|