Pringled commited on
Commit
da11bbe
Β·
verified Β·
1 Parent(s): 53f4973

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -7
README.md CHANGED
@@ -7,26 +7,30 @@ sdk: static
7
  pinned: false
8
  ---
9
 
10
- ## Hello, we're minish!
11
 
12
- We're a two-person ([@pringled](https://huggingface.co/Pringled) and [@stephantulkens](https://huggingface.co/stephantulkens)) open-source company, 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
- * Ingest the entire English Wikipedia in 5 minutes
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): make tiny models that are still really really good.
26
- * [potion](https://huggingface.co/minishlab/potion-base-8M): the best small model 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, approximate deduplication for your text datasets.
 
 
 
29
 
30
  You can also find us on:
31
  πŸ”¬ [GitHub](https://github.com/MinishLab)
32
  πŸ‘½ [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
  πŸ”¬ [GitHub](https://github.com/MinishLab)
35
  πŸ‘½ [LinkedIn](https://www.linkedin.com/company/minish-lab/)
36
+ πŸ’¬ [Discord](https://discord.gg/4BDPR5nmtK)