Iwan Kawrakow 8c936e3d65 bitnet: replace ggml_mul with ggml_scale to apply the scales ...

Also save one scale operation in the ffn network by adjusting
rms_eps. We gain up to 3% in performance by doing this, but it
is a bit of a hack (we store the tensor scales in op_params
while loading the model).

2024-06-22 12:02:52 +03:00

729 KiB

Raw Blame History

View Raw