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



·
AI & ML interests
Multilingual NLP
Recent Activity
upvoted
a
collection
8 days ago
🧠 SmolLM3
liked
a Space
8 days ago
nanotron/ultrascale-playbook
new activity
30 days ago
MaLA-LM/mala-opus-dedup-2410:[bot] Conversion to Parquet