almaghrabima commited on
Commit
344b20c
·
verified ·
1 Parent(s): 2d1f910

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -3
README.md CHANGED
@@ -29,8 +29,6 @@ This is the **SARF** (Sarf-Aware Representation Framework) tokenizer designed fo
29
  - Prefixes, suffixes, infixes
30
  - Tense, gender, number, and derivation
31
 
32
- > **Ṣarf is the exact linguistic layer that makes Arabic hard for naive tokenizers.**
33
-
34
  SARF combines morphological analysis with BPE tokenization to achieve better compression, especially for morphologically rich languages like Arabic.
35
 
36
  Most tokenizers treat Arabic as **bytes or characters**. **SARF treats Arabic as a *language*.**
@@ -47,7 +45,7 @@ Most tokenizers treat Arabic as **bytes or characters**. **SARF treats Arabic as
47
  ## Installation
48
 
49
  ```bash
50
- pip install deeplatent-nlp
51
  ```
52
 
53
  ## Quick Start
 
29
  - Prefixes, suffixes, infixes
30
  - Tense, gender, number, and derivation
31
 
 
 
32
  SARF combines morphological analysis with BPE tokenization to achieve better compression, especially for morphologically rich languages like Arabic.
33
 
34
  Most tokenizers treat Arabic as **bytes or characters**. **SARF treats Arabic as a *language*.**
 
45
  ## Installation
46
 
47
  ```bash
48
+ uv pip install deeplatent-nlp
49
  ```
50
 
51
  ## Quick Start