警告: warnings.warn(f'Input type into Linear4bit is torch.float16, but bnb_4bit_compute_type=torch.float32 (default). This will lead to slow inferenceortraining speed.') Run Code Online (Sandbox Code Playgroud) 硬件: DellPrecision T7920 Tower server/WorkstationIntelxeon gold processor @ 1...
pytorch Linear4bit的输入类型是torch.float16，但bnb_4bit_compute_type=torch.float32(默认),这会...