philschmid

README.md
*.pyc
*.pyo
*.pyd
__pycache__
.pytest_cache
serverless.yaml
get_model.py

philschmid

FROM public.ecr.aws/lambda/python:3.8

# Copy function code and models into our /var/task
COPY ./ ${LAMBDA_TASK_ROOT}/

# install our dependencies
RUN python3 -m pip install -r requirements.txt --target ${LAMBDA_TASK_ROOT}

# Set the CMD to your handler (could also be done as a parameter override outside of the Dockerfile)
CMD [ "handler.handler" ]

philschmid

https://download.pytorch.org/whl/cpu/torch-1.5.0%2Bcpu-cp38-cp38-linux_x86_64.whl
transformers==3.4.0

philschmid

import json
import torch
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, AutoConfig

def encode(tokenizer, question, context):
    """encodes the question and context with a given tokenizer"""
    encoded = tokenizer.encode_plus(question, context)
    return encoded["input_ids"], encoded["attention_mask"]

def decode(tokenizer, token):

philschmid

python3 get_model.py

philschmid

from transformers import AutoModelForQuestionAnswering, AutoTokenizer

def get_model(model):
  """Loads model from Hugginface model hub"""
  try:
    model = AutoModelForQuestionAnswering.from_pretrained(model,use_cdn=True)
    model.save_pretrained('./model')
  except Exception as e:
    raise(e)

philschmid

mkdir model & pip3 install torch==1.5.0 transformers==3.4.0

philschmid

serverless create --template aws-python3 --path serverless-multilingual

philschmid

{
  "context": "We introduce a new language representation model called BERT, which stands for idirectional Encoder Representations from Transformers. Unlike recent language epresentation models (Peters et al., 2018a; Radford et al., 2018), BERT is designed to pretrain deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be finetuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial taskspecific architecture modifications. BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5% (7.7% point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD 

philschmid

serverless deploy