dcy0577

[BUG] Inconsistent inference and evaluation results of the XLNET-CLM even on the training set!

2

### Bug description Hello, I followed the example and successfully trained an XLNet-CLM model on my custom dataset. However, I noticed that while the model performs well on the validation...

Save 4bits llama model to Torchscript failed

1

### System Info bitsandbytes=0.42.0 transformers=4.37.1 ### Reproduction ``` import torch import torch.nn as nn import transformers from transformers import BitsAndBytesConfig class Wrapper(nn.Module): def __init__(self): super().__init__() # get the llama model...

Multi-view feature augmented point cloud

6

Hi @maxjaritz, first thanks for your wonderful work! I plan to use KPConv to replace PointNet++ to do some experiments. I want to know whether the multi-view feature augmented point...

Understand the response from magma server for UI navigation

1

Hi, thanks for the excellent work! I deployed the FastAPI server on my machine via Docker. I used the `https://github.com/microsoft/Magma/blob/main/server/test_api.py` to test the model inference, simply replace the image and...