How to run a transformers bert without pipeline? - aws-lambda

Question

I have found myself dealing with an enviroment that does not support multiprocessing. How do I run my DistillBert without transformers pipeline?
Here is code right now:
import json
import os
import sys
sys.path.append("/mnt/access")
import torch
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
from transformers.pipelines import pipeline
def lambda_handler(event, context):
print("After:",os.listdir("/mnt/access"))
tokenizer = AutoTokenizer.from_pretrained('/mnt/access/Dis_Save/')
model = AutoModelForQuestionAnswering.from_pretrained('/mnt/access/Dis_Save/')
nlp_qa = pipeline('question-answering', tokenizer=tokenizer,model=model)
context = "tra"
question = "tra"
X = nlp_qa(context=context, question=question)
return {
'statusCode': 200,
'body': json.dumps('Hello from Lambda!')
}
Error message I get right now:
{
"errorMessage": "[Errno 38] Function not implemented",
"errorType": "OSError",
"stackTrace": [
" File \"/var/task/lambda_function.py\", line 18, in lambda_handler\n X = nlp_qa(context=context, question=question)\n",
" File \"/mnt/access/transformers/pipelines.py\", line 1776, in __call__\n features_list = [\n",
" File \"/mnt/access/transformers/pipelines.py\", line 1777, in <listcomp>\n squad_convert_examples_to_features(\n",
" File \"/mnt/access/transformers/data/processors/squad.py\", line 354, in squad_convert_examples_to_features\n with Pool(threads, initializer=squad_convert_example_to_features_init, initargs=(tokenizer,)) as p:\n",
" File \"/var/lang/lib/python3.8/multiprocessing/context.py\", line 119, in Pool\n return Pool(processes, initializer, initargs, maxtasksperchild,\n",
" File \"/var/lang/lib/python3.8/multiprocessing/pool.py\", line 191, in __init__\n self._setup_queues()\n",
" File \"/var/lang/lib/python3.8/multiprocessing/pool.py\", line 343, in _setup_queues\n self._inqueue = self._ctx.SimpleQueue()\n",
" File \"/var/lang/lib/python3.8/multiprocessing/context.py\", line 113, in SimpleQueue\n return SimpleQueue(ctx=self.get_context())\n",
" File \"/var/lang/lib/python3.8/multiprocessing/queues.py\", line 336, in __init__\n self._rlock = ctx.Lock()\n",
" File \"/var/lang/lib/python3.8/multiprocessing/context.py\", line 68, in Lock\n return Lock(ctx=self.get_context())\n",
" File \"/var/lang/lib/python3.8/multiprocessing/synchronize.py\", line 162, in __init__\n SemLock.__init__(self, SEMAPHORE, 1, 1, ctx=ctx)\n",
" File \"/var/lang/lib/python3.8/multiprocessing/synchronize.py\", line 57, in __init__\n sl = self._semlock = _multiprocessing.SemLock(\n"
]
}
Other code:
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
import torch
import json
import sys
sys.path.append("/mnt/access")
tokenizer = AutoTokenizer.from_pretrained("/mnt/access/Dis_Save/")
model = AutoModelForQuestionAnswering.from_pretrained("/mnt/access/Dis_Save/", return_dict=True)
def lambda_handler(event, context):
text = r"""
🤗 Transformers (formerly known as pytorch-transformers and pytorch-pretrained-bert) provides general-purpose
architectures (BERT, GPT-2, RoBERTa, XLM, DistilBert, XLNet…) for Natural Language Understanding (NLU) and Natural
Language Generation (NLG) with over 32+ pretrained models in 100+ languages and deep interoperability between
TensorFlow 2.0 and PyTorch.
"""
questions = ["How many pretrained models are available in 🤗 Transformers?",]
for question in questions:
inputs = tokenizer(question, text, add_special_tokens=True, return_tensors="pt")
input_ids = inputs["input_ids"].tolist()[0]
text_tokens = tokenizer.convert_ids_to_tokens(input_ids)
answer_start_scores, answer_end_scores = model(**inputs).values()
answer_start = torch.argmax(
answer_start_scores
) # Get the most likely beginning of answer with the argmax of the score
answer_end = torch.argmax(answer_end_scores) + 1 # Get the most likely end of answer with the argmax of the score
answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(input_ids[answer_start:answer_end]))
print(f"Question: {question}")
print(f"Answer: {answer}")
return {
'statusCode': 200,
'body': json.dumps(answer)
}
Edit:
I run the code. It runs well on it's own, however I get an error whne running on API itself:
{
"errorMessage": "'tuple' object has no attribute 'values'",
"errorType": "AttributeError",
"stackTrace": [
" File \"/var/task/lambda_function.py\", line 39, in lambda_handler\n answer_start_scores, answer_end_scores = model(**inputs).values()\n"
]
}