Skip to content

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度

180 B
Raw Blame
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