arxiv:2407.01996
Badr-Eddine Marani
badrmarani
AI & ML interests
None yet
Recent Activity
liked a model about 5 hours ago
Qwen/Qwen3-32B upvoted an article about 2 months ago
Evaluations with Chat Formats upvoted an article about 2 months ago
Efficient LLM Pretraining: Packed Sequences and Masked Attention