amazon/FalconLite2 · Trying to deploy this model with vllm in Sagemaker

I have a custom container built like so -

FROM deepjavalibrary/djl-serving:deepspeed-nightly

RUN apt-get update -y && \
 DEBIAN_FRONTEND=noninteractive apt-get install -y git && \
 apt-get clean && \
 rm -rf /var/lib/apt/lists/*

RUN pip3 install --no-cache-dir \
    "git+https://github.com/huggingface/transformers"

Pushed the image to ECR and referring the image_uri while creating the endpoint in Sagemaker.

Getting this error:

[WARN ] PyProcess - W-133-model-stderr: KeyError: 'transformer.h.0.mlp.dense_4h_to_h.bias'

How should I solve this issue ?