Kishin Nishik's picture

5

Kishin Nishik

Malum0x

·

AI & ML interests

None yet

Recent Activity

reacted to s3nh's post with ❤️ 2 days ago

Existing methods — GPTQ, AWQ, llama.cpp's k-quants — minimize empirical loss heuristically. None of them prove they are optimal in any information-theoretic sense. ICRB-Q builds a quantization scheme that is provably optimal via the Cramér-Rao lower bound (CRB): no unbiased estimator of a weight can have lower variance than [F(θ)]⁻¹, where F is the Fisher information matrix.

liked a model 29 days ago

Malum0x/mlp-surgery-restored-top30

updated a collection about 1 month ago

View all activity

Organizations

Malum0x 's models 5

Malum0x/mlp-surgery-restored-specificity-top10

3B • Updated May 7 • 5 • 1

Malum0x/mlp-surgery-restored-top30

3B • Updated May 7 • 6 • 2

Malum0x/mlp-surgery-restored-top15

3B • Updated May 7 • 4

Malum0x/mlp-surgery-restored-top5

3B • Updated May 7 • 3

Malum0x/mlp-surgery-broken

3B • Updated May 7 • 5