[Example Request] Deploying OpenChatKit model on SageMaker

**Describe the use case example you want to see**
Deploy the open source GPT-NeoXT-Chat-Base-20B (OpenChatKit) model across GPUs on SageMaker

**How would this example be used? Please describe.**

This example will demonstrate how to use SageMaker large model inference container to host OpenChatKit. Example uses DeepSpeed’s model parallel techniques with multiple GPUs on a single SageMaker machine learning instance. OpenChatKit also includes an extensible retrieval system. With the retrieval system the chatbot is able to incorporate regularly updated or custom content, such as knowledge from Wikipedia, news feeds, or sports scores in response. The additional component of OpenChatKit is a 6 billion parameter moderation model fine-tuned from GPT-JT. In chat applications, the moderation model runs in tandem with the main chat model, checking the user utterance for any inappropriate content. Based on the moderation model’s assessment, the chatbot can limit the input to moderated subjects. For more narrow tasks the moderation model can be used to detect out-of-domain questions and override when the question is not on topic Please refer to [this](https://www.together.xyz/blog/openchatkit) blog post to extend this model with retrieval system.

**Describe which SageMaker services are involved**
SageMaker Inference(hosting)

**Describe what other services (other than SageMaker) are involved***
Amazon S3, ECR

**Describe which dataset could be used. Provide its location in s3://sagemaker-sample-files or another source.**
NA

The request describes a SageMaker Inference hosting example for the GPT-NeoXT-Chat-Base-20B (OpenChatKit) model, using multiple GPUs and DeepSpeed. Start with the SageMaker large model inference container and the referenced OpenChatKit blog post; done means demonstrating deployment with Amazon S3 and ECR, including the model's retrieval and moderation components.

Written by the indexing model from the issue text.