Intel

/

gpt-j-6B-pytorch-int8-static-inc

like 0

Follow

Intel 2.39k

• "__torch__.intel_extension_for_pytorch.quantization._quantize_utils.___torch_mangle_1476.QuantizationDispatchModule",
• "torch.FloatStorage",
• "torch.LongStorage",
• "torch.DoubleStorage",
• "collections.OrderedDict",
• "torch._utils._rebuild_tensor_v2",
• "torch.QInt8Storage",
• "torch.ByteStorage",
• "torch.per_channel_affine",
• "torch._utils._rebuild_qtensor"

How to fix it?