Text-to-Audio
Transformers
English
Inference Endpoints

AWS Sagemaker error (400)

#1
by Osamaalam - opened

Deployed the Tango model on a SageMaker endpoint, but you’re encountering an error when trying to call it. Can anyone help me ?

Screenshot 2024-06-04 212546.png

I wanna know how to properly call this model. Used following code to deploy.

import sagemaker
import boto3
from sagemaker.huggingface import HuggingFaceModel

try:
role = sagemaker.get_execution_role()
except ValueError:
iam = boto3.client('iam')
role = iam.get_role(RoleName='sagemaker_execution_role')['Role']['Arn']

Hub Model configuration. https://huggingface.co/models

hub = {
'HF_MODEL_ID':'declare-lab/tango2',
'HF_TASK':'text-to-audio'
}

create Hugging Face Model Class

huggingface_model = HuggingFaceModel(
transformers_version='4.37.0',
pytorch_version='2.1.0',
py_version='py310',
env=hub,
role=role,
)

deploy model to SageMaker Inference

predictor = huggingface_model.deploy(
initial_instance_count=1, # number of instances
instance_type='ml.m5.xlarge' # ec2 instance type
)

I guess error is related to model_type its missing from config file can anyone tell me whats the model type? Please add it.

Sign up or log in to comment