Raichu

Hi @Nioolek Thank you for your nice PR. I am just doing the same thing as this PR does. By the way, I have tried your Dockerfile and got the...

Thanks for your rapid reply! Sorry for my confusing writing. What I want to point out is the mismatch between `MODEL['ANCHORS']` values and the commented anchor values. In other words,...

> Yeah, but it still looks fine to me. Anchor is only a starting point. So it won't affect the training that much as long as they are not too...

Thank you for your reply! I appreciate it. If there is any sample code, could you tell me the link? I found examples of combining vector_store with keyword table [here](https://github.com/jerryjliu/gpt_index/tree/main/examples/composable_indices),...

Thank you for your invitation! I will join.

I also encountered the same problem. I tried from notebook instance. Here is my implementation: ```py import sagemaker from sagemaker.pytorch import PyTorchModel from sagemaker.serverless import ServerlessInferenceConfig sagemaker_session = sagemaker.Session() role...

I solved this problem by changing how to create tar.gz file. The key point is to use `tar` command **in the same directory as the model file** like: ```bash $...

@chenscottus Firsr I tried to convert this model, it fails. Because the model contains numpy operation in the forward method, which cannot be converted into ONNX. Thus, you can convert...

Thank you for creating this issue. I am also in this trouble.

It seems this bug is occurred when I use the latest version: v4.42.0 I downgraded the version to v4.41.0, then the problem was solved