Valkyria-lenneth

Thanks for you project. But I found that the broadcasting in numpy is likely not supported in NumCpp. For example, I have two matrixs: A=[1,2,3] B = [[1], [2], [3]]...

I just want to reproduce the paper results. Since the paper use only bitnet-transformer, so I wonder if I can replace FC with this BitLienar for Transformer.

Cannot load the checkpoint

1

When I run segmentation notebook and try to load the model, it shows: UnpicklingError: invalid load key, 'v'. It seems the checkpoint is not suitable for the model. hope can...

Sagemaker + LMI async -> Invalid Default Sagemaker Metric

1

## Description Following the guidance of LMI15 async, the vllm config is ``` engine=Python option.async_mode=true option.rolling_batch=disable option.entryPoint=djl_python.lmi_vllm.vllm_async_service option.tensor_parallel_degree=max ``` However, Sagemaker default metrics are invalid and couldn't show the real...