Fix Q4_1_O optimization

This commit is contained in:
saharNooby 2023-04-18 16:46:27 +04:00
parent 2ef7ee0fac
commit 7b28076243
2 changed files with 2 additions and 2 deletions

View File

@ -90,7 +90,7 @@ python rwkv/quantize.py ~/Downloads/rwkv.cpp-169M.bin ~/Downloads/rwkv.cpp-169M-
Formats available:
- `4`: `Q4_1_O`, OK quality, fast (comparable to `FP16`).
- `4`: `Q4_1_O`, OK quality, moderately fast (20% slower than `FP16`).
- `3`: `Q4_1`, worst quality, fast (comparable to `FP16`).
- `2`: `Q4_0`, poor quality, very fast.

2
ggml

@ -1 +1 @@
Subproject commit fbf4d6052fd2df028169a5609a4f45fbbdf6eece
Subproject commit 538e516aced0aae5b22cbe7e691169e6957df753