Hi, I’m trying to deploy a serverless endpoint from model_data. Trying to do it in the same manner I deployed a similar model to an EC2 instance, but it seems to fail. I do huggingface_model = HuggingFaceModel(**model_params) where model_params = {‘role’: <exec_role>, ‘transformers_version’: ‘4.…

Serverless deploy troubles

AlexG May 16, 2022, 8:49am 5

@philschmid Thanks! I actually copied the exact implementation from your notebook for this test. Then placed it under “code” directory as you show…

Topic		Replies	Views
How to deploy a huggingface model from S3 outside a Jupyter Notebook Amazon SageMaker	6	3306	November 12, 2021
Getting error in the inference stage of Transformers Model (Hugging Face) 🤗Transformers	0	783	October 11, 2022
Deploying T5-style models via Sagemaker Endpoint: 'T5LayerFF' object has no attribute 'config' Amazon SageMaker	5	1465	November 7, 2022
InternalServerException from bart model created from s3 Amazon SageMaker	1	390	May 22, 2023
Need help deploying a HF model to AWS Sagemaker Amazon SageMaker	3	165	September 27, 2024