diff --git a/README.md b/README.md index 7ce6e00..43cd5c1 100644 --- a/README.md +++ b/README.md @@ -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. diff --git a/ggml b/ggml index fbf4d60..538e516 160000 --- a/ggml +++ b/ggml @@ -1 +1 @@ -Subproject commit fbf4d6052fd2df028169a5609a4f45fbbdf6eece +Subproject commit 538e516aced0aae5b22cbe7e691169e6957df753