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
about 14 hours ago
google/gemma-3-12b-it:Lack of `max_position_embeddings` in config.json
liked
a Space
4 days ago
C4AI-Community/m-rewardbench
new activity
4 days ago
Zihao-Li/Selfish:[bot] Conversion to Parquet
Organizations
Collections
1
models
38

Zihao-Li/V7-Bi-Code-Stag
Text Generation
•
Updated
•
5

Zihao-Li/V7-Bi-Code-Alt
Text Generation
•
Updated
•
2

Zihao-Li/V7-Bi-Code-Sel
Text Generation
•
Updated
•
2

Zihao-Li/V7-Mono-Alt
Text Generation
•
Updated
•
2

Zihao-Li/V7-Bi-Sel
Text Generation
•
Updated
•
1

Zihao-Li/V7-Bi-Stag
Text Generation
•
Updated
•
1

Zihao-Li/V7-Mono-Code-Alt
Text Generation
•
Updated
•
1

Zihao-Li/V7-Mono-Code-Sel
Text Generation
•
Updated
•
1

Zihao-Li/V7-Mono-Code-Stag
Text Generation
•
Updated
•
1

Zihao-Li/V7-Bi-Alt
Text Generation
•
Updated
•
1