llama.cpp
2-bit quantizations
#4897
Merged

2-bit quantizations #4897

ikawrakow merged 5 commits into master from ik/quantize-iq2
ikawrakow
imatrix: load
e9372e40
imatrix: WIP
8da2b25b
imatrix: Add Q2_K quantization
75f4cbf2
imatrix: also guard against Q2_K_S quantization without importance ma…
d5598f7e
imatrix: guard even more against low-bit quantization misuse
f342143e
kalomaze
JianbangZ
ikawrakow
ikawrakow
ggerganov
ggerganov commented on 2024-01-12
JianbangZ
ggerganov
ggerganov commented on 2024-01-12
ikawrakow
JianbangZ
kalomaze
ikawrakow
ikawrakow
JianbangZ
ggerganov
kalomaze
JianbangZ
8XXD8
ggerganov
ggerganov approved these changes on 2024-01-13
ikawrakow ikawrakow merged 147b17ac into master 2 years ago
ikawrakow ikawrakow deleted the ik/quantize-iq2 branch 2 years ago
ikawrakow
sorasoras
Nexesenex
gotzmann

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone