"""Compression recipe used to create this checkpoint. Run quantization from the original BF16 checkpoint, not from an already quantized checkpoint. """ from llmcompressor.modifiers.quantization import QuantizationModifier RECIPE = QuantizationModifier( targets="Linear", scheme="FP8_DYNAMIC", ignore=[ "re:.*vision_tower.*", "re:.*multi_modal_projector.*", "re:.*lm_head.*", ], )