Update README.md
Browse files
README.md
CHANGED
|
@@ -297,6 +297,9 @@ print(f"Chat completion output:{result}")
|
|
| 297 |
|
| 298 |
## Deploy the model on a SageMaker LMI Endpoint
|
| 299 |
|
|
|
|
|
|
|
|
|
|
| 300 |
Please refer to this [Jupyter Notebook](https://github.com/awslabs/extending-the-context-length-of-open-source-llms/tree/main/long-llava-qwen2-7b/notebooks/deploy-on-aws-sagemaker-long-llava-qwen2-7b.ipynb) to see how to deploy a Sagemaker [large model inference (LMI) container](https://docs.aws.amazon.com/sagemaker/latest/dg/large-model-inference-container-docs.html).
|
| 301 |
|
| 302 |
|
|
|
|
| 297 |
|
| 298 |
## Deploy the model on a SageMaker LMI Endpoint
|
| 299 |
|
| 300 |
+
**Important Note** - It is recommended to run the Jupyter notebook below on a [SageMaker Notebook instace](https://docs.aws.amazon.com/sagemaker/latest/dg/nbi.html). Please make sure your IAM role for the jupter Notebook instance
|
| 301 |
+
has full access to [AmazonEC2ContainerRegistryFullAccess](https://docs.aws.amazon.com/AmazonECR/latest/userguide/security-iam-awsmanpol.html)
|
| 302 |
+
|
| 303 |
Please refer to this [Jupyter Notebook](https://github.com/awslabs/extending-the-context-length-of-open-source-llms/tree/main/long-llava-qwen2-7b/notebooks/deploy-on-aws-sagemaker-long-llava-qwen2-7b.ipynb) to see how to deploy a Sagemaker [large model inference (LMI) container](https://docs.aws.amazon.com/sagemaker/latest/dg/large-model-inference-container-docs.html).
|
| 304 |
|
| 305 |
|