Introduction to JumpStart - Machine Translation
This notebook’s CI test result for us-west-2 is as follows. CI test results in other regions can be found at the end of the notebook.
Note: This notebook was tested on ml.t3.medium instance in Amazon SageMaker Studio with Python 3 (Data Science) kernel and in Amazon SageMaker Notebook instance with conda_python3 kernel.
1. Set Up
[ ]:
!pip install sagemaker ipywidgets --upgrade --quiet
Permissions and environment variables
[ ]:
import sagemaker, boto3, json
from sagemaker import get_execution_role
aws_role = get_execution_role()
aws_region = boto3.Session().region_name
sess = sagemaker.Session()
2. Select a model
Here, we download jumpstart model_manifest file from the jumpstart s3 bucket, filter-out all the Machine Translation models and select a model for inference. ***
[ ]:
from ipywidgets import Dropdown
# download JumpStart model_manifest file.
boto3.client("s3").download_file(
f"jumpstart-cache-prod-{aws_region}", "models_manifest.json", "models_manifest.json"
)
with open("models_manifest.json", "rb") as json_file:
model_list = json.load(json_file)
# filter-out all the Machine Translation models from the manifest list.
machine_translation_models = []
for model in model_list:
model_id = model["model_id"]
if "-translation-" in model_id and model_id not in machine_translation_models:
machine_translation_models.append(model_id)
# display the model-ids in a dropdown to select a model for inference.
model_dropdown = Dropdown(
options=machine_translation_models,
value="huggingface-translation-t5-base",
description="Select a model",
style={"description_width": "initial"},
layout={"width": "max-content"},
)
Different models are trained on different input and output languages. Default huggingface-translation-t5-base
model translates text from English to German.
[ ]:
display(model_dropdown)
[ ]:
# model_version="*" fetches the latest version of the model
model_id, model_version = model_dropdown.value, "*"
3. Retrieve JumpStart Artifacts & Deploy an Endpoint
Using JumpStart, we can perform inference on the pre-trained model, even without fine-tuning it first on a new dataset. We start by retrieving the deploy_image_uri
, deploy_source_uri
, and model_uri
for the pre-trained model. To host the pre-trained model, we create an instance of `sagemaker.model.Model
<https://sagemaker.readthedocs.io/en/stable/api/inference/model.html>`__ and deploy it. This may take a few minutes. ***
[ ]:
from sagemaker import image_uris, model_uris, script_uris, hyperparameters
from sagemaker.model import Model
from sagemaker.predictor import Predictor
from sagemaker.utils import name_from_base
endpoint_name = name_from_base(f"jumpstart-example-infer-{model_id}")
inference_instance_type = "ml.p2.xlarge"
# Retrieve the inference docker container uri. This is the base HuggingFace container image for the default model above.
deploy_image_uri = image_uris.retrieve(
region=None,
framework=None, # automatically inferred from model_id
image_scope="inference",
model_id=model_id,
model_version=model_version,
instance_type=inference_instance_type,
)
# Retrieve the inference script uri. This includes all dependencies and scripts for model loading, inference handling etc.
deploy_source_uri = script_uris.retrieve(
model_id=model_id, model_version=model_version, script_scope="inference"
)
# Retrieve the model uri. This includes the pre-trained model and parameters.
model_uri = model_uris.retrieve(
model_id=model_id, model_version=model_version, model_scope="inference"
)
# Create the SageMaker model instance
model = Model(
image_uri=deploy_image_uri,
source_dir=deploy_source_uri,
model_data=model_uri,
entry_point="inference.py", # entry point file in source_dir and present in deploy_source_uri
role=aws_role,
predictor_cls=Predictor,
name=endpoint_name,
)
# deploy the Model. Note that we need to pass Predictor class when we deploy model through Model class,
# for being able to run inference through the sagemaker API.
model_predictor = model.deploy(
initial_instance_count=1,
instance_type=inference_instance_type,
predictor_cls=Predictor,
endpoint_name=endpoint_name,
)
4. Query endpoint and parse response
[ ]:
def query(model_predictor, text):
"""Query the model predictor."""
encoded_text = text.encode("utf-8")
query_response = model_predictor.predict(
encoded_text,
{
"ContentType": "application/x-text",
"Accept": "application/json",
},
)
return query_response
def parse_response(query_response):
"""Parse response and return translated text."""
model_predictions = json.loads(query_response)
translation_text = model_predictions["translation_text"]
return translation_text
[ ]:
newline, bold, unbold = "\n", "\033[1m", "\033[0m"
input_text = "My name is Wolfgang and I live in Berlin"
query_response = query(model_predictor, input_text)
translation_text = parse_response(query_response)
print(
f"Input text: {input_text}{newline}"
f"Translation text: {bold}{translation_text}{unbold}{newline}"
)
5. Clean up the endpoint
[ ]:
# Delete the SageMaker endpoint
model_predictor.delete_model()
model_predictor.delete_endpoint()
This notebook was tested in multiple regions. The test results are as follows, except for us-west-2 which is shown at the top of the notebook.