Rethinking Multilingual Continual Pretraining: Data Mixing for Adapting LLMs Across Languages and Resources
Zihao Li
Zihao-Li



·
AI & ML interests
Multilingual NLP
Recent Activity
new activity
3 days ago
MaLA-LM/PolyWrite:Update dataset card: MaLA Corpus, improved description, and updated citations
updated
a Space
29 days ago
Zihao-Li/MT-HumanEval
Organizations
Collections
1
models
38

Zihao-Li/V7-Bi-Code-Stag
Text Generation
•
Updated
•
8

Zihao-Li/V7-Bi-Code-Alt
Text Generation
•
Updated
•
11

Zihao-Li/V7-Bi-Code-Sel
Text Generation
•
Updated
•
10

Zihao-Li/V7-Mono-Alt
Text Generation
•
Updated
•
12

Zihao-Li/V7-Bi-Sel
Text Generation
•
Updated
•
11

Zihao-Li/V7-Bi-Stag
Text Generation
•
Updated
•
9

Zihao-Li/V7-Mono-Code-Alt
Text Generation
•
Updated
•
8

Zihao-Li/V7-Mono-Code-Sel
Text Generation
•
Updated
•
9

Zihao-Li/V7-Mono-Code-Stag
Text Generation
•
Updated
•
15

Zihao-Li/V7-Bi-Alt
Text Generation
•
Updated
•
8