Spaces:
Configuration error
Configuration error
|
Download README.md from Team-13/Sentiment_analysis: direct link, hf CLI and curl.
- Browser
- Download file 1.54 kB
-
https://huggingface.co/spaces/Team-13/Sentiment_analysis/resolve/main/README.md
- Command line
-
hf download hf://spaces/Team-13/Sentiment_analysis/README.md
-
curl -L -o README.md https://huggingface.co/spaces/Team-13/Sentiment_analysis/resolve/main/README.md
1.54 kB
Text Sentiment Analyzer (Local)
A simple local Gradio app that classifies text sentiment using a Hugging Face Transformers pipeline
(distilbert-base-uncased-finetuned-sst-2-english). No remote APIs.
Quickstart
python -m venv .venv && source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txt
python app.py
Open the printed local URL and paste any text. Use the Neutral margin slider to make the classifier return NEUTRAL when POS vs NEG is too close to call.
Why this fits Deliverable 2
- Runs locally on your hardware (no
InferenceClient, no external API). - Clear contrast vs. your API-based product from Deliverable 1.
- Includes tests and a GitHub Action that runs
pyteston push/PR.
Project layout
sentiment_local/
ββ app.py
ββ sentiment.py
ββ requirements.txt
ββ README.md
ββ tests/
β ββ test_sentiment.py
ββ .github/workflows/
ββ ci.yml
Notes
- On the first run, Transformers will download the model weights to your machine
(cached under
~/.cache/huggingface/). Subsequent runs are fully local. - If you need strictly offline installs, pre-download the model:
python -c "from transformers import AutoTokenizer, AutoModelForSequenceClassification; \ AutoTokenizer.from_pretrained('distilbert-base-uncased-finetuned-sst-2-english'); \ AutoModelForSequenceClassification.from_pretrained('distilbert-base-uncased-finetuned-sst-2-english')"