Ideas & society2023 · shared on Hacker News
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
Explore SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Yjph00 ·
Fine tune a 70B language model at home
909 points206 comments
Ytosh ·
LLM.int8(): 8-Bit Matrix Multiplication for Transformers at Scale
15 points2 comments
Ymindcrime ·
ROCm Is AMD's #1 Priority, Executive Says
2 points0 comments
Yconvexstrictly ·
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
1 points1 comments