neuralink
neuralink
AI & ML interests
distributed training @nous research. ex-nanotron @huggingface
Recent Activity
upvoted a paper 1 day ago
Efficient Pre-Training with Token Superposition published a Space 16 days ago
neuralink/distill-blog-phuc upvoted a paper about 2 months ago
Shortcut-connected Expert Parallelism for Accelerating
Mixture-of-ExpertsOrganizations
