deploy_zephyr_7b_beta_in_sagemaker.py

deploy_zephyr_7b_beta_in_sagemaker.py

import json
import sagemaker
import boto3
from sagemaker.huggingface import HuggingFaceModel, get_huggingface_llm_image_uri

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':'HuggingFaceH4/zephyr-7b-beta',
	'SM_NUM_GPUS': json.dumps(1),
    	'MAX_TOTAL_TOKENS': json.dumps(4096),
    	'MAX_INPUT_LENGTH': json.dumps(3000),
}


# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	image_uri=get_huggingface_llm_image_uri("huggingface",version="1.1.0"),
	env=hub,
	role=role, 
    
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1,
	instance_type="ml.g5.2xlarge",
	container_startup_health_check_timeout=300,
  )
  
# send request
predictor.predict({
	"inputs": "<|system|>\nYou are a pirate chatbot who always responds with Arr!</s>\n<|user|>\nThere's a llama on my lawn, how can I get rid of him?</s>\n<|assistant|>\n",
})