llama.cpp
2-bit quantizations
#4897
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
5
Changes
View On
GitHub
2-bit quantizations
#4897
ikawrakow
merged 5 commits into
master
from
ik/quantize-iq2
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
ggerganov
commented on 2024-01-12
ggerganov
commented on 2024-01-12
ggerganov
approved these changes on 2024-01-13
ikawrakow
merged
147b17ac
into master
2 years ago
ikawrakow
deleted the ik/quantize-iq2 branch
2 years ago
Login to write a write a comment.
Login via GitHub
Reviewers
ggerganov
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub