Views
No views yet
Novaciano/NSFW_RP-3.2-1B-torchao-int8_weight_only. It has been quantized using int8_weight_only quantization with torchao.1from transformers import AutoModel
2
3model = AutoModel.from_pretrained("Novaciano/NSFW_RP-3.2-1B-torchao-int8_weight_only")