2 回答
- 最新
- 投票最多
- 评论最多
0
Here is a blog post on how deploy the laregest BLOOM model (176B parameters): https://aws.amazon.com/blogs/machine-learning/deploy-bloom-176b-and-opt-30b-on-amazon-sagemaker-with-large-model-inference-deep-learning-containers-and-deepspeed/
For smaller models you can leverage SageMaker Jumpstart: https://aws.amazon.com/blogs/machine-learning/run-text-generation-with-gpt-and-bloom-models-on-amazon-sagemaker-jumpstart/
已回答 2 年前