lpq29743 commited on
Commit
df073ce
1 Parent(s): 1510736

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -9,6 +9,7 @@ datasets:
9
  - cis-lmu/Glot500
10
  ---
11
 
 
12
 
13
  MaLA-500 is a novel large language model designed to cover an extensive range of 534 languages. This model builds upon LLaMA 2 7B and integrates continued pretraining with vocabulary extension, with an expanded vocabulary size of 260,164, and LoRA low-rank adaptation.
14
 
@@ -18,6 +19,8 @@ MaLA-500 is a novel large language model designed to cover an extensive range of
18
  - **Vocabulary Extension:** MaLA-500 boasts an extended vocabulary size of 260,164.
19
  - **Multilingual Proficiency:** Trained on Glot500-c, covering 534 languages.
20
 
 
 
21
  ## How to Get Started with the Model
22
 
23
  Requirements:
 
9
  - cis-lmu/Glot500
10
  ---
11
 
12
+ # MaLA-500: Massive Language Adaptation of Large Language Models
13
 
14
  MaLA-500 is a novel large language model designed to cover an extensive range of 534 languages. This model builds upon LLaMA 2 7B and integrates continued pretraining with vocabulary extension, with an expanded vocabulary size of 260,164, and LoRA low-rank adaptation.
15
 
 
19
  - **Vocabulary Extension:** MaLA-500 boasts an extended vocabulary size of 260,164.
20
  - **Multilingual Proficiency:** Trained on Glot500-c, covering 534 languages.
21
 
22
+ Please refer to [our paper](https://arxiv.org/pdf/2401.13303.pdf) for more details.
23
+
24
  ## How to Get Started with the Model
25
 
26
  Requirements: