Hugging Face's logo

Intel
/
gpt-neox-20b-int4-inc

English
Model card Files Community
yintongl commited on
Commit
c7485d7
•
1 Parent(s): acc19d5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -29,6 +29,7 @@ python3 main.py \
29
  --group_size 128 \
30
  --bits 4 \
31
  --iters 1000 \
 
32
  --deployment_device 'gpu' \
33
  --disable_quanted_input \
34
  --minmax_lr 2e-3 \
 
29
  --group_size 128 \
30
  --bits 4 \
31
  --iters 1000 \
32
+ --nsamples 512 \
33
  --deployment_device 'gpu' \
34
  --disable_quanted_input \
35
  --minmax_lr 2e-3 \