aasthavar

{
  'name': '76_B. Mice',
  'description': 'Modern researches has shown that a flock of hungry mice '
                 'searching for a piece of...',
  'public_tests': {'input': ['3 2 0 2\n0 1 3\n2 5\n'], 'output': ['1\n']},
  'private_tests': {'input': ['20 18 1 2\n'
                              '-9999944 -9999861 -9999850 -9999763 -9999656 '
                              '-9999517 -9999375 -999927...',
                              ...,
                              '7 11 10 20\n'

aasthavar

import boto3
import json

client = boto3.client('sagemaker-runtime')

input_text = """[INST] Hi! [/INST] 
Hello! How are you? 
[INST] I am great, thanks for asking. Could you help me with a task? [/INST]"""

input_data = {

aasthavar

import boto3
from pprint import pprint

client = boto3.client('sagemaker')

def main():
    endpoint_config_names = []

    for key in paginate(client.list_endpoint_configs):
        endpoint_config_names.append(key['EndpointConfigName'])

aasthavar

import boto3
from pprint import pprint

client = boto3.client('sagemaker')


def main():
    endpoint_names = []

    for key in paginate(client.list_endpoints):

aasthavar

import boto3
from pprint import pprint

client = boto3.client('sagemaker')


def main():
    model_names = []

    for key in paginate(client.list_models):

aasthavar

Quick Fixes

(Cuda Memory out error): Depends on the further error text
Option 1:
import gc
import torch
def report_gpu():
    print(torch.cuda.list_gpu_processes())
    gc.collect()
    torch.cuda.empty_cache()

aasthavar

# !pip install transformers datasets evaluate accelerate --quiet

import time
import warnings
warnings.filterwarnings("ignore")

from tqdm.auto import tqdm
import collections
import numpy as np

aasthavar

newline, bold, unbold = "\n", "\033[1m", "\033[0m"

text1 = "Translate to German:  My name is Arthur"
text2 = "A step by step recipe to make bolognese pasta:"


for text in [text1, text2]:
    query_response = query_endpoint(text.encode("utf-8"), endpoint_name=endpoint_name)
    generated_text = parse_response(query_response)
    print(

aasthavar

import logging
import sys

# Set up logging
logger = logging.getLogger(__name__)

logging.basicConfig(
    level=logging.getLevelName("INFO"),
    handlers=[logging.StreamHandler(sys.stdout)],
    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",

aasthavar

del model
del trainer
torch.cuda.empty_cache()