Francis Couture-Harpin 3a0bf17d57 gguf-py : Numpy (de)quantization for TQ1_0 and TQ2_0 ...

* ggml-quants : use roundf instead of nearest_int for TQ1_0 and TQ2_0

This does not change anything for ternary models,
since their values should never end up being in halfway cases anyway.

2024-08-12 00:06:48 -04:00

9.8 KiB

Executable File

Raw Blame History

View Raw