PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
addict modelscope gguf sentencepiece torchvision pillow numba pytest lm_eval>=0.4.10 # for transformers >= 5.0.0 diffusers protobuf compressed-tensors>=0.15.0 transformers>=5.5.0