Merge branch 'master' into python-string

Author: lpozo

.github/workflows/dircheck.py

@@ -46,7 +46,7 @@
             f"{f}: ensure folder name only uses "
             f"lowercase letters, numbers, and hyphens"
         )
-        has_error = True
+        has_errors = True
 
     files = sorted(_.name for _ in f.glob("*"))
     if "README.md" not in files:

huggingface-transformers/README.md

@@ -0,0 +1,42 @@
+# 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/).
+
+## Installation
+
+Create and activate a virtual environment, and then install the required dependencies:
+
+```sh
+(venv) $ python -m pip install transformers torch pillow notebook ipywidgets
+```
+
+Alternatively, if you use [Poetry](https://realpython.com/dependency-management-python-poetry/), then you can issue the following command to handle the installation process for you:
+
+```sh
+$ poetry install
+```
+
+## Usage
+
+Run the sample Python scripts:
+
+```sh
+(venv) $ python auto_classes.py
+(venv) $ python running_pipelines.py
+```
+
+Run the sample Jupyter notebook:
+
+```sh
+(venv) $ python -m jupyter notebook gpus_google_colab.ipynb
+```
+
+Note that if you run this notebook in Google Colab, then you'll need to update the path to the `requirements.txt` file and the `DATA_PATH` constant accordingly:
+
+```diff
+-!pip install -r requirements.txt
++!pip install -r /content/requirements.txt
+
+-DATA_PATH = "Scraped_Car_Review_dodge.csv"
++DATA_PATH = "/content/Scraped_Car_Review_dodge.csv"
+```

huggingface-transformers/Scraped_Car_Review_dodge.csv

@@ -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}")