Open YYyp99 opened 1 year ago
similar question here, how does one do batch prediction using the jumpstart models?
trying the same, but the model file doesnt seem to be a real tar
ClientError: An error occurred (ValidationException) when calling the CreateTransformJob operation: Model file at "s3://jumpstart-cache-prod-us-west-2/meta-infer/infer-meta-textgeneration-llama-2-7b-f.tar.gz" is not a GZipped file. Please ensure your model file is tarred and GZipped.
I used Sagemaker's Jumpstart to directly deploy the llama2-7b-chat model, and now I need to perform a batch conversion task. However, when using this model, there was a 'Need to pass custom' issue Attributes='accept Eula=true 'as part of header', how can I solve this problem
`import sagemaker from sagemaker.transformer import Transformer
sagemaker_session = sagemaker.Session()
transformer = Transformer( model_name='meta-textgeneration-llama-2-7b-f-20230915-031114', instance_count=1, instance_type='ml.g4dn.12xlarge', strategy='SingleRecord', assemble_with='Line', output_path='s3://output/', base_transform_job_name='batch-transform-job1', sagemaker_session=sagemaker_session ) transformer.transform( 's3://test.json', content_type='text/json', split_type='Line' )`