philschmid

from sagemaker.huggingface.model import HuggingFaceModel
from sagemaker.serverless import ServerlessInferenceConfig
from sagemaker.serializers import DataSerializer
import sagemaker
import boto3

try:
    role = sagemaker.get_execution_role()
except ValueError:
    iam = boto3.client('iam')

philschmid

apiVersion: argoproj.io/v1alpha1
kind: Workflow
metadata:
  generateName: xgboost-trainer-
  annotations: {pipelines.kubeflow.org/kfp_sdk_version: 1.8.12, pipelines.kubeflow.org/pipeline_compilation_time: '2022-04-19T13:58:21.551241',
    pipelines.kubeflow.org/pipeline_spec: '{"description": "A trainer that does end-to-end
      distributed training for XGBoost models.", "inputs": [{"default": "gs://{{kfp-default-bucket}}",
      "name": "output", "optional": true}, {"default": "{{kfp-project-id}}", "name":
      "project", "optional": true}, {"default": "HALT_ON_ERROR", "name": "diagnostic_mode",
      "optional": true}, {"default": "5", "name": "rounds", "optional": true}], "name":

philschmid

from sagemaker.huggingface import HuggingFaceModel
from sagemaker.serializers import DataSerializer
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models

hub = {
	'HF_MODEL_ID':'facebook/wav2vec2-base-960h',
	'HF_TASK':'automatic-speech-recognition'

philschmid

import time
import boto3
import os
import json
from locust import User, task, between

# How to use
# 1. install locust & boto3
#   pip install locust boto3
# 2. run benchmark via cli

philschmid

#!/usr/bin/env python3
from aws_cdk import core as cdk
import os
from pathlib import Path
import shutil
import subprocess

from aws_cdk import (
    aws_iam as iam,
    aws_sagemaker as sagemaker,

philschmid

from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
hub = {	'HF_MODEL_ID':'bigscience/T0_3B','HF_TASK':'text2text-generation'}
# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.6.1',
	pytorch_version='1.7.1',
	py_version='py36',

philschmid

import torch
import os
from transformers import Wav2Vec2Processor, HubertForCTC
from transformers.pipelines.automatic_speech_recognition import ffmpeg_read


def get_file_size(file_path):
    size = os.path.getsize(file_path)
    return f"{round(size / 1000 / 1000,2)} MB"

philschmid

import tarfile
import os

root = "./endpoint"


def main():
    cwd = os.getcwd()
    os.chdir(root)
    files = [os.path.join(path, name) for path, _, files in os.walk(".") for name in files]

philschmid

from argparse import ArgumentParser
from asyncio import get_event_loop, gather
from multiprocessing import Process

from requests import post, Session
from re import compile


from datasets import load_dataset
from elasticsearch import Elasticsearch

philschmid

const API_URL = "https:/{URL}/api/{TASK}"

async function query(payload) {
    const body = JSON.stringify(payload)
    try {
        const response = await fetch(API_URL, {
            method: 'post',
            body
        })
        return response.json();