Merge pull request #543 from hfhoffman1144/huggingface-transformers

Huggingface transformers

huggingface-transformers/README.md

@@ -0,0 +1,24 @@
+# Hugging Face Transformers: Leverage Open-Source AI in Python
+
+This folder contains the materials for the tutorial (Hugging Face Transformers: Leverage Open-Source AI in Python)[https://realpython.com/huggingface-transformers/].
+
+Transformers is available on [PyPI](https://pypi.org/) and you can install it with [pip](https://realpython.com/what-is-pip/). Open a terminal or command prompt, create a new virtual environment, and then run the following command:
+
+```console
+(venv) $ python -m pip install transformers
+```
+
+This command will install the latest version of Transformers from PyPI onto your machine. Throughout this tutorial, you'll also leverage [PyTorch](https://realpython.com/pytorch-vs-tensorflow/) to interact with models at a lower level. You can install PyTorch with the following command:
+
+```console
+(venv) $ python -m pip install torch
+```
+
+To verify that the installations were successful, start a [Python REPL](https://realpython.com/python-repl/) and import `transformers` and `torch`:
+
+```pycon
+>>> import transformers
+>>> import torch
+```
+
+If the imports run without errors, then you've successfully installed the dependencies needed for this tutorial.

huggingface-transformers/auto_classes.py

@@ -0,0 +1,25 @@
+import torch
+from transformers import (
+    AutoConfig,
+    AutoModelForSequenceClassification,
+    AutoTokenizer,
+)
+
+model_name = "cardiffnlp/twitter-roberta-base-sentiment-latest"
+
+config = AutoConfig.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+text = "I love using the Transformers library!"
+encoded_input = tokenizer(text, return_tensors="pt")
+
+with torch.no_grad():
+    output = model(**encoded_input)
+
+scores = output.logits[0]
+probabilities = torch.softmax(scores, dim=0)
+
+for i, prob in enumerate(probabilities):
+    label = config.id2label[i]
+    print(f"{i + 1}) {label}: {prob}")