diff --git a/config_sample.yml b/config_sample.yml index 070c1d1b..94f7ad51 100644 --- a/config_sample.yml +++ b/config_sample.yml @@ -103,7 +103,7 @@ model: # Disable Flash-attention 2. Set to True for GPUs lower than Nvidia's 3000 series. (default: False) #no_flash_attention: False - # Enable 8 bit cache mode for VRAM savings (slight performance hit). + # Enable different cache modes for VRAM savings (slight performance hit). # Possible values FP16, FP8, Q4. (default: FP16) #cache_mode: FP16