docs: changed the link to more helpful source (#20411)

docs: changed a link to better source

[Previous
link](https://www.philschmid.de/custom-inference-huggingface-sagemaker)
is about how to upload embeddings model.
[New
link](https://huggingface.co/blog/kchoe/deploy-any-huggingface-model-to-sagemaker)
is about how to upload cross encoder model, which directly addresses
what is needed here. For full disclosure, I wrote this article and the
sample `inference.py` is the result of this new article.

Co-authored-by: Kenny Choe <kchoe@amazon.com>

docs/docs/integrations/document_transformers/cross_encoder_reranker.ipynb

@@ -175,7 +175,7 @@
    "source": [
     "## Uploading Hugging Face model to SageMaker endpoint\n",
     "\n",
-    "Refer to [this article](https://www.philschmid.de/custom-inference-huggingface-sagemaker) for general guideline. Here is a simple `inference.py` for creating an endpoint that works with `SagemakerEndpointCrossEncoder`.\n",
+    "Here is a sample `inference.py` for creating an endpoint that works with `SagemakerEndpointCrossEncoder`. For more details with step-by-step guidance, refer to [this article](https://huggingface.co/blog/kchoe/deploy-any-huggingface-model-to-sagemaker). \n",
     "\n",
     "It downloads Hugging Face model on the fly, so you do not need to keep the model artifacts such as `pytorch_model.bin` in your `model.tar.gz`."
    ]