Text Classification
Transformers
Safetensors
English
distilbert
beginner
tutorial
huggingface-course
sentiment-analysis
text-embeddings-inference
Instructions to use naomienaija/huggingface-course-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use naomienaija/huggingface-course-models with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="naomienaija/huggingface-course-models")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("naomienaija/huggingface-course-models") model = AutoModelForSequenceClassification.from_pretrained("naomienaija/huggingface-course-models", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Hugging Face Course Models
This repository was created as part of a Hugging Face Transformers course.
Purpose
The repository demonstrates how to:
- download a pretrained model;
- save it with
save_pretrained(); - inspect the generated model files;
- publish the files to the Hugging Face Hub;
- reload the model from a personal repository.
Model
The current model is based on:
distilbert/distilbert-base-uncased-finetuned-sst-2-english
Task
Text classification / sentiment analysis.
Labels
- NEGATIVE
- POSITIVE
Intended Use
Educational demonstration of the Hugging Face publishing workflow.
Limitations
This repository republishes an existing pretrained model for educational purposes. It is not a newly trained model.
License
MIT
- Downloads last month
- 17