News for hackers. Stuff that matters.

A comment on DeepSeek-R1. Parent comment

Re:DeepSeek-R1 by DominikPeters on Tuesday January 21, 2025 @09:53AM (#42780737)
Indeed, for each of the words it got it right.
[ Parent | on HN ]
Re:DeepSeek-R1 by bt1a on Tuesday January 21, 2025 @12:31PM (#42782842)
How excellent for a quantized 27GB model (the Q6_K_L GGUF quantization type uses 8 bits per weight in the embedding and output layers since they're sensitize to quantization)
[ Parent | on HN ]