GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Paper • 2403.03507 • Published • 191
Jeong seungwoo
hangsiin
AI & ML interests
Vision, NLP, Self-training, Data science, AI Ethics
Recent Activity
liked a model 22 days ago
ideogram-ai/ideogram-4-nf4 liked a model 30 days ago
pyannote/speaker-diarization-3.1 liked a model about 1 month ago
prism-ml/bonsai-image-ternary-4B-gemlite-2bitOrganizations
None yet
upvoted 4
papers over 2 years ago
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Paper • 2402.19427 • Published • 58
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 630
Genie: Generative Interactive Environments
Paper • 2402.15391 • Published • 72