Skip to content

Commit 001e5ef

Browse files
authored
Change lowbit example to use 4-bit as default in example (#10865)
As titled
1 parent ed80e3b commit 001e5ef

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

examples/models/llama/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -398,7 +398,7 @@ LLAMA_CHECKPOINT=path/to/checkpoint.pth
398398
LLAMA_PARAMS=path/to/params.json
399399

400400
# Set low-bit quantization parameters
401-
QLINEAR_BITWIDTH=3 # Can be 1-8
401+
QLINEAR_BITWIDTH=4 # Can be 1-8
402402
QLINEAR_GROUP_SIZE=128 # Must be multiple of 16
403403
QEMBEDDING_BITWIDTH=4 # Can be 1-8
404404
QEMBEDDING_GROUP_SIZE=32 # Must be multiple of 16

0 commit comments

Comments
 (0)