Skip to content

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度

Commits on main

update readme (#242)
n1ck-guo committed 2 years ago
5d92b25
add runable script for autoround (#225)
n1ck-guo committed 2 years ago
e15cf35
move some settings from example to main (#241)
wenhuach21 committed 2 years ago
ec20b59
refine the code and the speedup is notable (#240)
wenhuach21 committed 2 years ago
46f23b9
add tritonv2, improve packing and pbar (#239)
wenhuach21 committed 2 years ago
a5337c8
bedbf5d
add brief formats introduction (#236)
wenhuach21 committed 2 years ago
a6ab57a
Update model link (#232)
WeiweiZhang1 committed 2 years ago
4455478
add meta3.1-70B model, refine docs (#231)
WeiweiZhang1 committed 2 years ago
a9af34d
add quantized models by 3rd party (#230)
WeiweiZhang1 committed 2 years ago
985189f
change the scale thresh generally (#229)
WeiweiZhang1 committed 2 years ago
b2f160c
refine example (#224)
WeiweiZhang1 committed 2 years ago
ac77f1e
Enable phi3v tuning (#197)
WeiweiZhang1 committed 2 years ago
f2fef13
948f228
update readme (#220)
wenhuach21 committed 2 years ago
1f1fe1a
add qwen int4 model, refine example (#217)
WeiweiZhang1 committed 2 years ago
fed34b7
avoid underflow and overflow for exllamav2 (#218)
wenhuach21 committed 2 years ago
04678e0
fix a bug in autoround format inference (#215)
wenhuach21 committed 2 years ago
a5f79c4
update xpu format exporting (#214)
WeiweiZhang1 committed 2 years ago
90d9fc0
remove local pile file (#213)
WeiweiZhang1 committed 2 years ago
c05c49b
fix example typo (#212)
WeiweiZhang1 committed 2 years ago
77a7e60
limit the scale minimum value not to 0 (#211)
WeiweiZhang1 committed 2 years ago
1dd2708
modify setup.py (#206)
n1ck-guo committed 2 years ago
8610b88
add local file of pile-10k (#198)
WeiweiZhang1 committed 2 years ago
084f3db
remove coverage check (#202)
Sun, Xuehao committed 2 years ago
081556f
support autoawq format (#115)
yintong-lu committed 2 years ago
b08b967