python 18 lines · 1 tab

Using Hugging Face transformers for modern NLP inference

Dr. Elena Vasquez Apr 2026

1 tab

from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline

model_name = 'distilbert-base-uncased-finetuned-sst-2-english'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

classifier = pipeline(
    task='text-classification',
    model=model,
    tokenizer=tokenizer,
    truncation=True,
)

texts = [
    'The checkout flow is fast and intuitive.',
    'Customer support never replied to my ticket.',
]
print(classifier(texts))

1 file · python Explain with highlit

I use transformers when the text task justifies contextual modeling and the serving budget can handle it. The fastest path to value is usually starting with pretrained checkpoints, measuring latency, and then deciding whether quantization, distillation, or simpler baselines are sufficient. Fancy models still need boring operational discipline.

Related snips

python

from gensim.models import Word2Vec

sentences = [
    ['customer', 'refund', 'payment', 'issue'],
    ['login', 'authentication', 'password', 'reset'],
    ['delivery', 'shipment', 'tracking', 'delay'],

Word embeddings with gensim for semantic similarity tasks

word-embeddings gensim nlp

by Dr. Elena Vasquez 1 tab

python

from datasets import Dataset
from transformers import AutoTokenizer, AutoModelForSequenceClassification, TrainingArguments, Trainer

model_name = 'distilbert-base-uncased'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=3)

Fine tuning transformer models for domain text classification

hugging-face fine-tuning transformers

by Dr. Elena Vasquez 1 tab

python

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.metrics import classification_report

pipeline = Pipeline([

Text vectorization with TF-IDF for strong classical baselines

tf-idf nlp text-classification

by Dr. Elena Vasquez 1 tab

python

import spacy
from spacy.matcher import Matcher

nlp = spacy.load('en_core_web_sm')
matcher = Matcher(nlp.vocab)
matcher.add('INCIDENT_ID', [[{'TEXT': {'REGEX': '^INC-[0-9]{6}$'}}]])

Natural language processing with spaCy pipelines and custom rules

spacy nlp entity-extraction

by Dr. Elena Vasquez 1 tab

Share this code

Here's the card — post it anywhere.

Using Hugging Face transformers for modern NLP inference — share card

Link copied