Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
@@ -7,26 +7,30 @@ sdk: static
|
|
7 |
pinned: false
|
8 |
---
|
9 |
|
10 |
-
## Hello, we're
|
11 |
|
12 |
-
We're a two-person ([@pringled](https://
|
13 |
|
14 |
We believe that if you make models fast enough, you unlock new possibilities.
|
15 |
|
16 |
Using our software, you can:
|
17 |
-
*
|
18 |
-
* Classify tens of thousands of documents per second on CPU
|
19 |
* Approximately deduplicate extremely large datasets in minutes
|
20 |
* Build the fastest RAG application in the world
|
21 |
* Easily evaluate which ANN algorithm works best for your data
|
22 |
|
23 |
Our projects:
|
24 |
|
25 |
-
* [model2vec](https://github.com/MinishLab/model2vec):
|
26 |
-
* [potion](https://huggingface.co/minishlab/potion-
|
27 |
* [vicinity](https://github.com/MinishLab/vicinity): consistent interfaces to many approximate nearest neighbor algorithms.
|
28 |
-
* [semhash](https://github.com/MinishLab/semhash): lightning-fast, super accuracte,
|
|
|
|
|
|
|
29 |
|
30 |
You can also find us on:
|
31 |
π¬ [GitHub](https://github.com/MinishLab)
|
32 |
π½ [LinkedIn](https://www.linkedin.com/company/minish-lab/)
|
|
|
|
7 |
pinned: false
|
8 |
---
|
9 |
|
10 |
+
## Hello, we're Minish!
|
11 |
|
12 |
+
We're a two-person ([@pringled](https://github.com/Pringled) and [@stephantul](https://github.com/stephantul)) open-source lab, with a focus on Natural Language Processing.
|
13 |
|
14 |
We believe that if you make models fast enough, you unlock new possibilities.
|
15 |
|
16 |
Using our software, you can:
|
17 |
+
* Embed the entire English Wikipedia in 5 minutes
|
18 |
+
* Classify tens of thousands of documents per second on a CPU
|
19 |
* Approximately deduplicate extremely large datasets in minutes
|
20 |
* Build the fastest RAG application in the world
|
21 |
* Easily evaluate which ANN algorithm works best for your data
|
22 |
|
23 |
Our projects:
|
24 |
|
25 |
+
* [model2vec](https://github.com/MinishLab/model2vec): tiny static embedding models with state-of-the-art performance.
|
26 |
+
* [potion](https://huggingface.co/collections/minishlab/potion-6721e0abd4ea41881417f062): the best small models in the world. 100-500x faster than a sentence-transformer, and almost as good.
|
27 |
* [vicinity](https://github.com/MinishLab/vicinity): consistent interfaces to many approximate nearest neighbor algorithms.
|
28 |
+
* [semhash](https://github.com/MinishLab/semhash): lightning-fast, super accuracte, semantic deduplication and filtering for your text datasets.
|
29 |
+
* [model2vec-rs](https://github.com/MinishLab/model2vec-rs): a Rust port of model2vec.
|
30 |
+
|
31 |
+
|
32 |
|
33 |
You can also find us on:
|
34 |
π¬ [GitHub](https://github.com/MinishLab)
|
35 |
π½ [LinkedIn](https://www.linkedin.com/company/minish-lab/)
|
36 |
+
π¬ [Discord](https://discord.gg/4BDPR5nmtK)
|