| 123456789101112131415161718 |
- # Example terraform.tfvars for minimal Amazon SageMaker deployment
- # Copy this file to terraform.tfvars and customize as needed
- # AWS Configuration
- aws_region = "us-east-1"
- # Project Configuration
- project_name = "my-llama-api"
- environment = "dev"
- # Model Configuration
- model_image_uri = "763104351884.dkr.ecr.us-east-1.amazonaws.com/huggingface-pytorch-inference:2.0.0-transformers4.28.1-gpu-py310-cu118-ubuntu20.04"
- model_data_s3_path = "s3://my-bucket/model/model.tar.gz" # Update with your model path
- model_name = "Llama-3.3-70B-Instruct"
- # Instance Configuration
- instance_type = "ml.p4d.24xlarge" # GPU instance for Llama models
- initial_instance_count = 1
|
